diff --git "a/SpeechT5_TTS_Fine_tuning_for_urdu.ipynb" "b/SpeechT5_TTS_Fine_tuning_for_urdu.ipynb" --- "a/SpeechT5_TTS_Fine_tuning_for_urdu.ipynb" +++ "b/SpeechT5_TTS_Fine_tuning_for_urdu.ipynb" @@ -1,2959 +1,1599 @@ { - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "2RosoNrCxVng" - }, - "source": [ - "# Fine-tuning SpeechT5 for multilingual TTS" - ] + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "gpuType": "T4" }, - { - "cell_type": "markdown", - "metadata": { - "id": "uELTb9CcOaCp" - }, - "source": [ - "This notebook demonstrates how to fine-tune the SpeechT5 model from 🤗 Transformers on the **text-to-speech** task.\n", - "\n", - "The unique thing about SpeechT5 is that the model is first pre-trained on a combination of speech-to-text and text-to-speech data, so that it learns a unified space of hidden representations shared by both text and speech. This allows us to fine-tune the same pretrained model on different tasks. Read more about SpeechT5 [in our blog post](https://huggingface.co/blog/speecht5).\n", - "\n", - "In this notebook we will start from an existing fine-tuned TTS model that was originally trained on English speech from LibriTTS, and fine-tune it for the Urdu Language.\n", - "\n", - "This TTS model will support multiple speakers through x-vector speaker embeddings." - ] + "kernelspec": { + "name": "python3", + "display_name": "Python 3" }, - { - "cell_type": "markdown", - "metadata": { - "id": "5xB8fh-ht4kK" - }, - "source": [ - "## Install required packages\n", - "\n", - "We install Transformers from GitHub since not all the SpeechT5 features we need have been merged into an official release yet.\n" - ] + "language_info": { + "name": "python" }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "5cd4197ba6cb43a79e8e48e3281d556a": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_37034519aba0437a89c974c344cc58be", + "IPY_MODEL_69a2281cd24c473fa2f4874034bfe1bd", + "IPY_MODEL_506636dde3f4495fa929c659ecf8b764" + ], + "layout": "IPY_MODEL_67fd8b2359ec4585a548b52f614531f1" + } }, - "id": "xJe8TF3atyqL", - "outputId": "964d222e-94c0-4de8-be56-59d67c3c148d" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Collecting datasets\n", - " Downloading datasets-2.20.0-py3-none-any.whl (547 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m547.8/547.8 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: soundfile in /usr/local/lib/python3.10/dist-packages (0.12.1)\n", - "Collecting speechbrain\n", - " Downloading speechbrain-1.0.0-py3-none-any.whl (760 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m760.1/760.1 kB\u001b[0m \u001b[31m38.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.15.4)\n", - "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.25.2)\n", - "Collecting pyarrow>=15.0.0 (from datasets)\n", - " Downloading pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl (39.9 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m39.9/39.9 MB\u001b[0m \u001b[31m13.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n", - "Collecting dill<0.3.9,>=0.3.0 (from datasets)\n", - " Downloading dill-0.3.8-py3-none-any.whl (116 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m15.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.0.3)\n", - "Collecting requests>=2.32.2 (from datasets)\n", - " Downloading requests-2.32.3-py3-none-any.whl (64 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m64.9/64.9 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: tqdm>=4.66.3 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.4)\n", - "Collecting xxhash (from datasets)\n", - " Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m16.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hCollecting multiprocess (from datasets)\n", - " Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: fsspec[http]<=2024.5.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n", - "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.5)\n", - "Requirement already satisfied: huggingface-hub>=0.21.2 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.23.5)\n", - "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.1)\n", - "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n", - "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.10/dist-packages (from soundfile) (1.16.0)\n", - "Collecting hyperpyyaml (from speechbrain)\n", - " Downloading HyperPyYAML-1.2.2-py3-none-any.whl (16 kB)\n", - "Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from speechbrain) (1.4.2)\n", - "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from speechbrain) (1.11.4)\n", - "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from speechbrain) (0.1.99)\n", - "Requirement already satisfied: torch>=1.9 in /usr/local/lib/python3.10/dist-packages (from speechbrain) (2.3.1+cu121)\n", - "Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (from speechbrain) (2.3.1+cu121)\n", - "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0->soundfile) (2.22)\n", - "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n", - "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n", - "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n", - "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n", - "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n", - "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n", - "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.21.2->datasets) (4.12.2)\n", - "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (3.3.2)\n", - "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (3.7)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (2.0.7)\n", - "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (2024.7.4)\n", - "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain) (1.13.0)\n", - "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain) (3.3)\n", - "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain) (3.1.4)\n", - "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n", - "Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n", - "Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n", - "Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n", - "Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n", - "Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n", - "Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n", - "Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n", - "Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n", - "Collecting nvidia-nccl-cu12==2.20.5 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl (176.2 MB)\n", - "Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.9->speechbrain)\n", - " Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n", - "Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain) (2.3.1)\n", - "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.9->speechbrain)\n", - " Downloading nvidia_nvjitlink_cu12-12.5.82-py3-none-manylinux2014_x86_64.whl (21.3 MB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.3/21.3 MB\u001b[0m \u001b[31m62.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hCollecting ruamel.yaml>=0.17.28 (from hyperpyyaml->speechbrain)\n", - " Downloading ruamel.yaml-0.18.6-py3-none-any.whl (117 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.8/117.8 kB\u001b[0m \u001b[31m15.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n", - "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n", - "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n", - "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n", - "Collecting ruamel.yaml.clib>=0.2.7 (from ruamel.yaml>=0.17.28->hyperpyyaml->speechbrain)\n", - " Downloading ruamel.yaml.clib-0.2.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl (526 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m526.7/526.7 kB\u001b[0m \u001b[31m48.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.9->speechbrain) (2.1.5)\n", - "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.9->speechbrain) (1.3.0)\n", - "Installing collected packages: xxhash, ruamel.yaml.clib, requests, pyarrow, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, dill, ruamel.yaml, nvidia-cusparse-cu12, nvidia-cudnn-cu12, multiprocess, nvidia-cusolver-cu12, hyperpyyaml, datasets, speechbrain\n", - " Attempting uninstall: requests\n", - " Found existing installation: requests 2.31.0\n", - " Uninstalling requests-2.31.0:\n", - " Successfully uninstalled requests-2.31.0\n", - " Attempting uninstall: pyarrow\n", - " Found existing installation: pyarrow 14.0.2\n", - " Uninstalling pyarrow-14.0.2:\n", - " Successfully uninstalled pyarrow-14.0.2\n", - "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", - "cudf-cu12 24.4.1 requires pyarrow<15.0.0a0,>=14.0.1, but you have pyarrow 17.0.0 which is incompatible.\n", - "google-colab 1.0.0 requires requests==2.31.0, but you have requests 2.32.3 which is incompatible.\n", - "ibis-framework 8.0.0 requires pyarrow<16,>=2, but you have pyarrow 17.0.0 which is incompatible.\u001b[0m\u001b[31m\n", - "\u001b[0mSuccessfully installed datasets-2.20.0 dill-0.3.8 hyperpyyaml-1.2.2 multiprocess-0.70.16 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.5.82 nvidia-nvtx-cu12-12.1.105 pyarrow-17.0.0 requests-2.32.3 ruamel.yaml-0.18.6 ruamel.yaml.clib-0.2.8 speechbrain-1.0.0 xxhash-3.4.1\n" - ] - } - ], - "source": [ - "!pip install datasets soundfile speechbrain" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" + "37034519aba0437a89c974c344cc58be": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_c8be0944b2d14e47a2f7909138527aaf", + "placeholder": "​", + "style": "IPY_MODEL_11d479256d314d3eab585386482e318b", + "value": "preprocessor_config.json: 100%" + } }, - "id": "HQCuMz3fwuHa", - "outputId": "d1509a7b-505f-47db-aa74-9fb8341e787a" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Collecting git+https://github.com/huggingface/transformers.git\n", - " Cloning https://github.com/huggingface/transformers.git to /tmp/pip-req-build-m7fgjodb\n", - " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers.git /tmp/pip-req-build-m7fgjodb\n", - " Resolved https://github.com/huggingface/transformers.git to commit 96a074fa7e2c04b904f72d9e827398d4c5f90f25\n", - " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", - " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", - " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", - "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (3.15.4)\n", - "Requirement already satisfied: huggingface-hub<1.0,>=0.23.2 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (0.23.5)\n", - "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (1.25.2)\n", - "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (24.1)\n", - "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (6.0.1)\n", - "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (2024.5.15)\n", - "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (2.32.3)\n", - "Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (0.19.1)\n", - "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (0.4.3)\n", - "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (4.66.4)\n", - "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.23.2->transformers==4.43.0.dev0) (2023.6.0)\n", - "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.23.2->transformers==4.43.0.dev0) (4.12.2)\n", - "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.43.0.dev0) (3.3.2)\n", - "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.43.0.dev0) (3.7)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.43.0.dev0) (2.0.7)\n", - "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.43.0.dev0) (2024.7.4)\n", - "Building wheels for collected packages: transformers\n", - " Building wheel for transformers (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", - " Created wheel for transformers: filename=transformers-4.43.0.dev0-py3-none-any.whl size=9403605 sha256=c2505d30926e465339b5e53f7c1b7963724dddf757ce1523549bfbc390ce681b\n", - " Stored in directory: /tmp/pip-ephem-wheel-cache-b7r1edg2/wheels/e7/9c/5b/e1a9c8007c343041e61cc484433d512ea9274272e3fcbe7c16\n", - "Successfully built transformers\n", - "Installing collected packages: transformers\n", - " Attempting uninstall: transformers\n", - " Found existing installation: transformers 4.42.4\n", - " Uninstalling transformers-4.42.4:\n", - " Successfully uninstalled transformers-4.42.4\n", - "Successfully installed transformers-4.43.0.dev0\n" - ] - } - ], - "source": [ - "!pip install git+https://github.com/huggingface/transformers.git" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" + "69a2281cd24c473fa2f4874034bfe1bd": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_115279124c584e2daa48346a7c9c8e9c", + "max": 433, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_350f730b810f4bd88740a77a7e0a51be", + "value": 433 + } }, - "id": "NfX4YNbs_HKP", - "outputId": "414c91dc-0e2f-4cc4-a2e3-bc15af8f0bf8" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (0.32.1)\n", - "Requirement already satisfied: numpy<2.0.0,>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate) (1.25.2)\n", - "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (24.1)\n", - "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n", - "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate) (6.0.1)\n", - "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.3.1+cu121)\n", - "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.23.5)\n", - "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.4.3)\n", - "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.15.4)\n", - "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (4.12.2)\n", - "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (1.13.0)\n", - "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.3)\n", - "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.4)\n", - "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2023.6.0)\n", - "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.105)\n", - "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (8.9.2.26)\n", - "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.3.1)\n", - "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (11.0.2.54)\n", - "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (10.3.2.106)\n", - "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (11.4.5.107)\n", - "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.0.106)\n", - "Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.20.5)\n", - "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.105)\n", - "Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.3.1)\n", - "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.0->accelerate) (12.5.82)\n", - "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (2.32.3)\n", - "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (4.66.4)\n", - "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.5)\n", - "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.3.2)\n", - "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.7)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2.0.7)\n", - "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2024.7.4)\n", - "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate) (1.3.0)\n" - ] - } - ], - "source": [ - "!pip install --upgrade accelerate" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "g_Xffd7sRlpk" - }, - "source": [ - "Do we have a GPU?" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" + "506636dde3f4495fa929c659ecf8b764": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_c16b239971bc41d8be09280b34536fd4", + "placeholder": "​", + "style": "IPY_MODEL_e92855e89e3e4ebba0159c6f24004aad", + "value": " 433/433 [00:00<00:00, 32.7kB/s]" + } }, - "id": "-XLi4c9DRnxA", - "outputId": "6d793249-e445-4b81-c0b7-8d14192bf4c8" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Mon Jul 22 19:12:49 2024 \n", - "+---------------------------------------------------------------------------------------+\n", - "| NVIDIA-SMI 535.104.05 Driver Version: 535.104.05 CUDA Version: 12.2 |\n", - "|-----------------------------------------+----------------------+----------------------+\n", - "| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |\n", - "| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |\n", - "| | | MIG M. |\n", - "|=========================================+======================+======================|\n", - "| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |\n", - "| N/A 48C P8 9W / 70W | 0MiB / 15360MiB | 0% Default |\n", - "| | | N/A |\n", - "+-----------------------------------------+----------------------+----------------------+\n", - " \n", - "+---------------------------------------------------------------------------------------+\n", - "| Processes: |\n", - "| GPU GI CI PID Type Process name GPU Memory |\n", - "| ID ID Usage |\n", - "|=======================================================================================|\n", - "| No running processes found |\n", - "+---------------------------------------------------------------------------------------+\n" - ] - } - ], - "source": [ - "!nvidia-smi" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "bmdgnloAQPQ1" - }, - "source": [ - "In case no GPU is found, from the menu choose **Runtime > Change runtime type** and set **Hardware accelerator** to **GPU**. Then restart the runtime to activate the GPU." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "GB6Ur8DHuUy8" - }, - "source": [ - "## Load the model\n", - "\n", - "We'll start from SpeechT5 that's already been fine-tuned for English TTS, and fine-tune it again but for a new language. For more info about the original checkpoint, you can find its model card on the [Hugging Face Hub](https://huggingface.co/microsoft/speecht5_tts)." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 365, - "referenced_widgets": [ - "5cd4197ba6cb43a79e8e48e3281d556a", - "37034519aba0437a89c974c344cc58be", - "69a2281cd24c473fa2f4874034bfe1bd", - "506636dde3f4495fa929c659ecf8b764", - "67fd8b2359ec4585a548b52f614531f1", - "c8be0944b2d14e47a2f7909138527aaf", - "11d479256d314d3eab585386482e318b", - "115279124c584e2daa48346a7c9c8e9c", - "350f730b810f4bd88740a77a7e0a51be", - "c16b239971bc41d8be09280b34536fd4", - "e92855e89e3e4ebba0159c6f24004aad", - "b89a27c225cf4e49860c8f62e32efaf6", - "fa94d043df65408a8418026350b837a1", - "169d1b4d3773401688dc1884d6532788", - "beb62f2bd7a24f9a82159ed016abb9b5", - "601c4fb9215444efb45f55852abd41d5", - "6bfda8329c3741f4a0f175d41603c707", - "877842a378c54836880b45d7b072c51b", - "fec3ab0d0be74c40a868ca3969e533c5", - "16951d20b1294e08b42339d08f97ae7b", - "91b3dc6e9a85404c96fd59cfb800d43f", - "b9290e687dcd420abfc46b43639fed28", - "64917c2ed79841e3a5080ffbe11baba8", - "976a925fc43c42f1a580fd808d32023d", - "9bf02a53411646439af4b7412d707923", - "fadd75cae7824fa598fd58ae994259ab", - "d7cd149116154f98aad430d857c46381", - "db176eb9bc144f5cbcacb0086d176571", - "fc0efaa60a504ffebb5e00bdc8c205b1", - "869df80d498642f4b3a1d1825372cef7", - "3518110403534f7f82a617d1bedc6315", - "e74722fed6a94c5bae623ed75c362a45", - "ec62796f2d86461ab698738058d21f82", - "f9735b84f4d3473a8307e736305cf252", - "0ba493d747144e1daac6252c6accc886", - "4138156fdfcf4d41947457d9670425df", - "eb350c3ec4bd4451b395c7fbd5f48f17", - "99d7ad89bdd346909213390a050f412f", - "9ecef1d0b473411b914eed7fa043478e", - "d827d96e5328476c80a212fad5570c78", - "22f4b0480fd34920b9a2e0c9d8c609dc", - "3f9e48a1f9014418825baa991e0f422c", - "cdb0d85e5dcb4d5998049b784acb00be", - "aaebe1f70f4f4d639d3ecbba9f406f8b", - "992902679da84067b429893c7870b816", - "af9cb18856474687a449ac515ede62e8", - "db44aadde79b40f1850078024e910183", - "f16031daae714a0181ddd0b31471f060", - "e7bdbfe7797a4b5db827f5b810d2d79b", - "a99df968c26040e3a9d8465d539b7844", - "45e7d7b493fb45d1b71b0f42464a9ac8", - "1eabe7caf021425a83295181e16a573d", - "e281d772babb4a2dbb1a949e6a5a440c", - "82d5d05b953042f4bc7ad53a122d6a03", - "786cb3e450de464fa04f9ed4fbe073e1", - "6c036b53916642e3993b40b66532f305", - "f02b5874bc1a4b29a0a8f65a455ae425", - "73bbb254a9f94a2f90776da888b551c2", - "4b400af9107d4cb09725a19a8978d33a", - "decda57cc9a7489fb32d384c270f4994", - "9b62f1cf2fe54ccda160abe4a281ca82", - "1073b875d7e040d1b96adc59ac722133", - "22f2f7b6cad948efa54f0c748d427777", - "ba3d74aab1d44f44a3b795f4e4a9177e", - "0a6f959beecf45f4ba2d1cb19f21a3bc", - "efd7335a34584dcab1c2ece372c23332", - "f093bd48a659437692d44be6308d0a53", - "140712a8dbb04cdd8dd7854cc1b579e5", - "980d09ee15b540a0868ed5e1cae7d867", - "616095ba34964997a82d5103681ec8fd", - "6d8d46c27f5e4d23a9170c06fb8e6947", - "1715e69a4fb84798b1d8d081991d0e65", - "bb212e00ea9b416db52167e0a64608ee", - "304787fbe0984b9f887fc948a8b888fc", - "e4138b99226846e9b4cfc4ea075329cd", - "f969b09762794b8f99ad8e2121945bc4", - "5348d94bb7114057bd7b3cb9885a0041" - ] - }, - "id": "W7spxtTGtmba", - "outputId": "0dc03789-0b00-4a88-b99c-40c395d2b8b2" - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: \n", - "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", - "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n", - "You will be able to reuse this secret in all of your notebooks.\n", - "Please note that authentication is recommended but still optional to access public models or datasets.\n", - " warnings.warn(\n" - ] + "67fd8b2359ec4585a548b52f614531f1": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "5cd4197ba6cb43a79e8e48e3281d556a", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "preprocessor_config.json: 0%| | 0.00/433 [00:00=1.9 in /usr/local/lib/python3.10/dist-packages (from speechbrain==1.0.0) (2.3.1+cu121)\n", - "Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (from speechbrain==1.0.0) (2.3.1+cu121)\n", - "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from speechbrain==1.0.0) (4.66.4)\n", - "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from speechbrain==1.0.0) (0.23.5)\n", - "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (3.15.4)\n", - "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (4.12.2)\n", - "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (1.13.0)\n", - "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (3.3)\n", - "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (3.1.4)\n", - "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (2023.6.0)\n", - "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.105)\n", - "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.105)\n", - "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (8.9.2.26)\n", - "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.3.1)\n", - "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (11.0.2.54)\n", - "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (10.3.2.106)\n", - "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (11.4.5.107)\n", - "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.0.106)\n", - "Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (2.20.5)\n", - "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.105)\n", - "Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (2.3.1)\n", - "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.9->speechbrain==1.0.0) (12.5.82)\n", - "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->speechbrain==1.0.0) (6.0.1)\n", - "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->speechbrain==1.0.0) (2.32.3)\n", - "Requirement already satisfied: ruamel.yaml>=0.17.28 in /usr/local/lib/python3.10/dist-packages (from hyperpyyaml->speechbrain==1.0.0) (0.18.6)\n", - "Requirement already satisfied: ruamel.yaml.clib>=0.2.7 in /usr/local/lib/python3.10/dist-packages (from ruamel.yaml>=0.17.28->hyperpyyaml->speechbrain==1.0.0) (0.2.8)\n", - "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.9->speechbrain==1.0.0) (2.1.5)\n", - "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->speechbrain==1.0.0) (3.3.2)\n", - "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->speechbrain==1.0.0) (3.7)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->speechbrain==1.0.0) (2.0.7)\n", - "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->speechbrain==1.0.0) (2024.7.4)\n", - "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.9->speechbrain==1.0.0) (1.3.0)\n" - ] - } - ], - "source": [ - "!pip install git+https://github.com/speechbrain/speechbrain.git@develop\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 177, - "referenced_widgets": [ - "d8e8d1b0adcd4d47b061aad1486604cb", - "1f15ee66a1f24e41b5630d5616243a7b", - "651b513c24e24a5990591f95f24a4c0a", - "708e0de686af4966a72d66fb174c1cfa", - "f46eb3dacc954c729a2c2b44d91a5382", - "db9886b3bdf24a7690e5464275656dca", - "5c7aa125de6544cf9ff580cceb311c9e", - "f0297cf643064c4c97df2e0749207379", - "caaca6fb45eb453dbd2d8bb4ff5d3d52", - "c78ec4ad3bfb443982281085989394fe", - "032cf630889f4f599dad2a0f718dd63e", - "59b8375db47b41709137a8831f06a693", - "969bec5ee95248d4a948965c74ff3311", - "8f604dc7fccf4572821cb040ab5d8c5c", - "677cfd9f2d3f4f669e488d12d21b8e20", - "974b89e5205a4487acb8577df5ea85e6", - "3e0e63681dfe4201ae9d8b7a370fca52", - "630aa4eac24e481a9fdb9d999f0c8822", - "6b988b31851c4db6890479404c7011cf", - "27b0e9d94b0a4d8cac920df223606d10", - "9d8b343299174f5789bfef21e23cfff6", - "8c299f76bb244a748838b967e5d93c2f", - "1fff9026fa29474ca2b652a2e0e98235", - "eebdffbf80d542a0bdea7e2e4f66fbe8", - "7827a86376c94da99efb90f5842864ed", - "d8c83b57302a458aa3ee71cac9632455", - "08a04116a15043e88c1c50b76bc3a77b", - "e1f400ffbb124a56a281832bcc54eaf9", - "a3ef8ad842a346df9ffc0f31725c9606", - "fa605877967d4109a4fd496e63e663ca", - "c1cb1e279bdd4de0a725dd51a8489563", - "37f6208a83084b92a458e21c197cad3f", - "1e1213f764474d7bbd426a5327829eb9", - "5492a2c2d56844bdabc9aaaab9bdc35f", - "669272db738947e2b8102102a57bc87a", - "dad194753c8e439c9d62285c0c06546a", - "ae2f4d6301694356b5878fab0de3ea83", - "156fa699696c4e26b2842e89954d202b", - "b0cda3f2c228491bb6ce981267141f52", - "3fb43042ede944c485c1eadf21ebfa96", - "7eecca112ead43c9ab55a5220122ce97", - "5f90e9766c3b44f0bded6715e12682d5", - "b01b07d8119c4485ab5844ce7351aad8", - "bb435b975d2844879538ba5b00c377b5", - "1c0c9d45f86f4945965a4784109020ff", - "8462433da1b847b09f137a5017b575c8", - "6535f9ad0436497dbcec30c1df342ac9", - "4d02d845fa034829900635be82eb64ad", - "6d274c81d3ed486a90598cee551db717", - "b58864d3bfb7426995ef989334687286", - "04512216d85b42c4ae02d3f1083acbe9", - "10aea82371aa4b23bb1e2f906778f92e", - "935177cdab4a419ebb327a9641c2a6ff", - "a10a271823244bce91dbc042bf838746", - "265bbe545b99430f85aa5884b64ac014" - ] - }, - "id": "smJs3_VB1Da2", - "outputId": "b8c498cb-603a-4761-8f16-849cb8d1ca49" - }, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "d8e8d1b0adcd4d47b061aad1486604cb", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "hyperparams.yaml: 0%| | 0.00/2.04k [00:00` to mark the end of the sentence." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 35 - }, - "id": "uu8PgZqH07lW", - "outputId": "9559a4fa-c992-4971-f5be-201d41e77335" - }, - "outputs": [ - { - "data": { - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "string" - }, - "text/plain": [ - "'kash yh wqt kbhy nh gzre.'" - ] - }, - "execution_count": 17, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "tokenizer.decode(processed_example[\"input_ids\"])" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "wOdMw-xa2u_8" - }, - "source": [ - "Speaker embeddings should be a 512-element vector:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" + "9bf02a53411646439af4b7412d707923": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_869df80d498642f4b3a1d1825372cef7", + "max": 238473, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_3518110403534f7f82a617d1bedc6315", + "value": 238473 + } }, - "id": "uuybSBq32AuH", - "outputId": "de2838f0-c816-48df-d28d-dcd72a800d6f" - }, - "outputs": [ - { - "data": { - "text/plain": [ - "(512,)" - ] - }, - "execution_count": 18, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "processed_example[\"speaker_embeddings\"].shape" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "YzyoPE2y2zHk" - }, - "source": [ - "The labels should be a log-mel spectrogram with 80 mel bins." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 216 + "fadd75cae7824fa598fd58ae994259ab": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_e74722fed6a94c5bae623ed75c362a45", + "placeholder": "​", + "style": "IPY_MODEL_ec62796f2d86461ab698738058d21f82", + "value": " 238k/238k [00:00<00:00, 12.4MB/s]" + } }, - "id": "dKu2km552GL-", - "outputId": "6498e8bd-a15f-49c3-996e-f1f9c31c25c2" - }, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAh8AAADHCAYAAAC5rzG6AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOz9TYw1S3YWjD5rRWTmrqr3r89puxtwc+HqSvx8SCAZMAYJIWThKcIDpDsBxNC2BM0EDy7Id2IxggGGETIjC4QEQjCwhCxhhGQLyYwYGN3fD66b/j39vm9V7do7MyLWHayfiNxV7+nu79rN+XwrpDrvqV25MyMjIyOetdaznkUiInhuz+25Pbfn9tye23P7PjX+n92B5/bcnttze27P7bn9/1d7Bh/P7bk9t+f23J7bc/u+tmfw8dye23N7bs/tuT2372t7Bh/P7bk9t+f23J7bc/u+tmfw8dye23N7bs/tuT2372t7Bh/P7bk9t+f23J7bc/u+tmfw8dye23N7bs/tuT2372t7Bh/P7bk9t+f23J7bc/u+tmfw8dye23N7bs/tuT2372t7Bh/P7bk9t+f23J7bc/u+tt828PHzP//z+H2/7/fhcDjgR37kR/Cf/tN/+u261HN7bs/tuT235/bc/nfUflvAxz//5/8cX/7yl/F3/+7fxX/+z/8Zf/SP/lH8+I//OL7+9a//dlzuuT235/bcnttze27/O2r021FY7kd+5EfwJ/7En8A//If/EADQWsOXvvQl/PRP/zT+9t/+25/63dYavvKVr+Dly5cgot/qrj235/bcnttze27P7behiQhub2/xu3/37wbzp/s28m/1xdd1xa//+q/jZ37mZ+IzZsaP/diP4Vd/9VcfHX8+n3E+n+P33/zN38Qf/sN/+Le6W8/tuT235/bcnttz+z60//7f/zt+6Id+6FOP+S0HH9/85jdRa8UXvvCF3edf+MIX8Bu/8RuPjv+5n/s5/OzP/uyjz/+X//P/Be/++IT0esX/6YvfwJIKXkxnMAQMwU1e8TKfkKgBAI51RpGEJoQmjNs6o7SEU81owjjXhCqMc8l4uZzxxcN7/K7DO3xhegcmdf58Y3uJ9+UKXzu/wtoSXuUTJq6oQkgkmLmC0cAkKJLwUDPWllEk4eP5Hm/yES/SGVd8xkNbcGoZ/+vDxzjWGe+3gw649RcAtsY4bjPWmnDaJtzdL6j3E0AASIAyIEcSQAgQgCoBBEhuduwwcO7HanosCAALUO2gqQFJwEn7IUKQysCJgSzgqwKy6/tpr65XXE0byMbptE2oQijWP3dQEQGJG66mDcwNiQRVCCKEKgwRwsM6oRRCWTOk2bUBcK7a7cp6n5WAZvcB9DHx+yG7VyHQykAFSPRYieOGYVkq0qGCUwUngdh3/d8mBAihbnZ9QK9fPozeqWgfZRaABem6YFo2/Knf87/iB5dbfC4fMVHFi/SAz/E9fv/0CSZqWEhQpT+qR+e1f5P9z9iDBqAIsArjfVvwSbvGb5x/N/77w8e4rxPWlrE2fQ98XmdumLngdy/v8GY64n9ZfhMv+ITP8QkzNWTSayQAExESCGT/fqhV632R9ui4y+9WCEQkvuN/2yBYRfAghHdtxv8ob/CN+hLf2F5iogomwftyhYc64dR0zh3rgiKMtSY0YRRhHNKG33P1Dh9Nd/h9yzfxmo/4fLrDx3zG51MGg5GIcJKCIg3frISj6HtbQag2wgkNCYIr3nCgihckmIiwUHp075f37Pf21H2OxzQAdXA2V3umAFAvJoQAqCBswjhJwl1bcNsOuJMDXvMRL/iMl3TGRA0MQaJ+gk04vnuWjHftCqc244yMKoQGxgs644bPuOIVMyretwVnmfC1+hpNCBNVJGpgNDQwTm0Ck2CmgokqMiqajd1Xtzd4Xw9gCBbe8Cev/5/4iB/wgvW9PjZGA+EkCRM1vOaCKkCBPvtv1xsstOFABZkqEgRHmbBJwv+ob3BqE+7aAU1svaCGhTZc8xkv+YxVEgoSMvS73vx+AaCB8a5eI0HwuXwHhmBCxRkZb+s1RBibJB2zNuHYZqwt4912wKlN+ObDDbaqc2FKFV+8vsVMBVepYBPCXTngk9M1vnH/AuctYVsz6kMGNgb5etyga/ckup4lW9e3cZ3Dbr2H9LVNJ4Wtc1PTF5cuJ85+n4jv+fn9d98fCBBfU7PNRl/3GvQaue9bSAJiifWTbjN4ZcxvCXJ/wv/9H/9f8fLlS3yn9lsOPr7X9jM/8zP48pe/HL+/f/8eX/rSl5DTAXw1ga8Z+WbBkgmHqSFTw8IFV4mw8BTgYyszILogNRCmMiMJg2whTi1jrQlSJixLw811wjJPuJp0CCoYWK+BcoDwFaRm8AIQNbCQPrtUbKHQp8Y1IwmjtgyeK3hqmHLDzILSJrQ2YU4ztjIjrQuaEIj1DEyCWhNymVBKBq0TqB7AZeqb7DQACNhk8gnMgOQPR8zINm/Jw0ZNUPDBAnbgIkArDKQEsICWqhOLAGIFINMNMC9AIgGTIFVGbYyt7Dc5IkFOhEPW44gEW00ojSGN0QTgNIFLAqcEqQyxF4kXXaSoEdBIP28GQnw84ubQPxMAk73c1f7MeoyQ6EsrgCwNfF3AqSIlQWv24sRLTbYIMCQWCuqgLa49jHklUCMdYxbwzYa8MA4vM5Z5wpQnTMSYueKQVyw5x0axScK9TI+emy+cTLoR9t/7dYswqiTUdoC0a8x5xpwmbHUGtRRz3r/HJJiYkQ8L5lzAhwMSCyautpYJKoANQIWCxgmCMizil0AoMK5dJw3DlCFI1DdZX08Zvgn4RkuAJIhkUDtAyjW4XAHbNUAVRA0oV+CWMUtCFcJ5WyDCqNsSgFHyBL4+I80FeVmwpA03mXHDjCv2KwJZBALCVCcskvHQrrFKwibZ7qHhQBtu+AimAnABIGjUHgEEHxu/b/98G6yBbXieAPRaNoI+bgoQFAR5m8iAuDBWJJzahA0JpzajygRqEyQBjRPONKFRjU3Z506fKwlNMmq9hkhCaQsqGE0YNWUIJyQmJKqYZUZrM15URgXjQBXJgGQF4cqeJ4Mxk4BJ+1jBOGwZW/VxTEjX+hyY1HBbRDftRQgLATfMqAKczCih1jCRIIHBNhTHeqX3W66QJSG1BSSMKozEBZkSiBNyEohkQFIYhwfaFDg1BR+bZO1n0z7OaTKwpuPJ9QoVhCSMrU1gSWjlgK3OqHlBLRMIV6Cms5i4Qa4KhCsqF2wto5YJja6BdgClDKIMpgRsHC+NgxBJgyEFAJn2wIPR16ARgIgZPdLX9tgHhr0iruWf27+ShnMPjfw/3p+pX1ctk+ELDlTMQKWawcxIM0FWO993QZn4LQcfn//855FSwte+9rXd51/72tfwxS9+8dHxy7JgWZbHHTtL3xjG47ngVX7AxBUTVdRAqwnn1m/nRdZRqEIoTdHsscw414xMFWyjr5NSvSVvt2u83a7w7nyFIow5FWRqKMJgkji/b7hMDac6Ya0Z92lG5ooDb5guFgP/ThXGebPJz1VBUqo4lYxSGVIYVAiS0CcBBtBRSfc+gW6cvvn6WsP2/0Kgqt9rS+sABFBQcbGRUxKdlADknCBZwFPV83BDTg1zqrjKGzL3he1+m/W+GgfYmLliyQWlKUBZa8JaDIAIoZSEVlkBj2/urEiaSSCsnpLGBkISKRhigRTW481bAX+RpgYR6uMw3KtUe1lJAjiIqIdFsN/Ud+ynYcGIlkTBG3QMZWNIRRzHNlZugW4tAwwFGm3Be1nQGmOVhK+W1/haef1onvjGcaACpqbWJ1qAbH3M+v8nmcNCY2q4SlvM12LPRI9Xq7g0xrHN+Hp5hXtecM8LNsk4mYV5alPM34QGphYbsy/mExUAQLV+NzAmKjjQpkMEXfgnqjjZgp+sv/5e3Msc1/X3974teFev8a5e4X05xL0+1FnfRS5IJGggrDXjbl1QhUAAGggPdcJdWfA2X+OaNYy7CuNeGo6iFvcmWe9TJpxkwv/t/EUc24xPyk3073U+4kvTJzYOj+/Vwcp4T958HXFPykQFs/29CuMkE+6bgqYAAFBvzibJvAyC63QO0HKSjLvax2OhggNvuG2HOMbP0UBqzXPBSz7F82+2+fq5tpZQwXidDnidj9hSwjWfcZIJTRhv0hGJGq7pbM+832MTHQMfj5OoV+qaz2BquKsHVGHctqv4rnuUmBpe0oaZ1F+yAdjAmKjhB9J9eGp0fiT89+1jHNsSwKwZ8Di2GUkyGq8KGNBQofPI20t+wA2vu35uZpz6vD7Zuc5twiflxua8rvPnlvHJeoO7bcF9mbHVhOM2KVAigQCx9r/HAaUxHsqE+3VGKUnXucK6js+trz1mVNHGBiDipdZjpxaeZwipIVR0nVTo3AEFnxWwNDPQqBEkiXlVDGjIsH/4dWwN23lBNt57mr35r6MR5gZhQniYJQm4EHDGd91+y8HHPM/44R/+YfzyL/8y/uJf/IsAlET6y7/8y/ipn/qp7/o8jQ3dNcJDUXffIRW0ZBu/hV9OBjqKJJSWkLmqhQ5dqLyVpn+vjbG2rK5MW7ireUsAXfyJ9KE1ITQiC+Xo/0dTVwjWqm7uzc6vIEhfyE2SbgT20ozW6Ng3wAABiwEF21SbQtmYRGQbpLvuaJyM3fLXE3Z0TUIaioB+VxyBeBcGdA0hoIlOeoguuCVhzUm9Na1hybooT1whQljtnpZUwCTIVNGIsFnvErvbXfsvI6hkvVdpfXwDBBgo6ffkIOriBUnWeX9BnkD84dlwV6G7NWNcOOabvoQX4zZeUgjShvNfembQLdtmm87UKk5NPR0b+iLJ1HYAxP//hAzI3nJ2YOIL+bHNONYlzuvHMBTIlWabhLm+H9IMroK7ekATwoE2tbqFcGq6IdfGg+W9D0kwySMgBCgYmqnims8GPArYwhmbJGzQkGeiFhuTbjTmdRS1/o9txtbSbjwmrpjQjQW2e59SBTcGkeimHRstB8jYqGKTZsCDd96F/XjugUQfh96XVRIa9D3eA6rSn91FaAJAgA+/zkwFIAM01p3RWGHzvgDqiVkk70CGP3v/fSJ9Qh/luzhXooZrVgDjgEjnoM0/yjhLxnXSsMs1679J7J6g57ihFUwNM1qM3YYUc7aiBRBhWzO9OdC64bOGZqgY4ND3bBrmUBPChsfPZ6KChTlAw6WR6WC5pb3XJ0FwkhmtsYE9xklygBcdnzXGa6MUAKYK4nq+dvv6z0MYeatJ9yXbZ9wIc3CiN9YNK18jwuHX7JhxfWPphqGvkaMXREi/l2D7gx1j67z4sb62ATtPuS7Gsr/muBaTAZWxjd6SOE76+aDnp2aOwsvY4ae035awy5e//GX8lb/yV/DH//gfx5/8k38S/+Af/APc39/jr/21v/Zdn6PO0BsvjLvzAhHCzAVXadsd91AnPLQZD1VjwovFDIujc2FswliN/7HWhHPNuN0OuxipbxYLV2TWRbIM7mufjAAwczGww9hawlYTDmnDwgV3ZUFNjIeq4ON2W3CqE7aq5/KNe7wmkajVPFVsy/DwG2E0xwXQyVJ8YuokJiJQA6gAknSySMbToQoPx/hsItHrtO7SE3Ds1SDBOmccLYSSuOE1CeZUMafa3e7c8Go+xSbh45O5gacNKydslXHCZBu3vYlJXzgp+k0RC/ewgFjHRoTQKulxBsRGYMFTM7Bl3pKV9i5LO04tBF3AYZ4athexFgMeVX941TEghoIjnys+/uO5ud+HL1Axj4XxrlwDGTjKEl4LALjmVTcdO9xd8FvLOLUJDYTNAIRbdc6FmKjifTngk+0GMxdM1JCpIhOwpoIGwrHMqI2ROGHlhswVW1MQ+To94No2hmob9rlNOGOK69UBBBzbHDwAJsGBN/Oo9Pv5fL7F75m+rZuzSLdUZdHN2zbuT8oLuxd9F5gEx7bgth7wUCecW9ZNhARXvIa3zb05TIKrvMWGMHPBxNov9+Dctqt4NifzdswDOmeoVb7whhe2ebnH4bZe7fpXwWFQKNDplvwIBjZJONYlPA9TqjjQZptqxkQF1zjHmPkmP84VQEEMG8irwtgm9bacmm7ox9Y9xQfacOANX8xvNWREm4FECU9CBeHYFpxkwvt2wG29wrEt+IH8Hh+lO7ziEw5UsNqacEMFDMHhAmRuIGxSFcwhYUWK8ejjKgA1vK3XMWcdkDZh3ErCgQoOol6LCQ3vZMH7dsBMNc41UcWbdMRJNjMSFWSfW8ZDnbGJrrELV7zLV1i44JpXfYZU1MMjCbf2r4PFCgXXr9MxgFojtvcWasiap7w0/RnXOAB4WPUdeYdDzN+x5dTUAeCci9R0PTOAII10bVXbEgDCyHIOmn9GDizcVcRk/AxdF30N1YnT94UI1TTqHpHcgNzAucV3PeytRhh1z7n0c0CgvDbY7wnKAZG+zlIh8ArQ/0zPBwD85b/8l/GNb3wDf+fv/B189atfxR/7Y38Mv/RLv/SIhPodm1mitZFOBEk4m3cBQLy4VUhJVGJgAMm8DdQRbEuBSrea8H47hJUOYHC3KTg5lzxspH0RzhcvJGDgwX6AbjH6RPYJ3IRw3HTi+vwAgPOW1U0n1F1uQJ9coytsnOdiccBxIyQACR+02OMc1a5D9l1H5hP2yBhArYTV+pdTxZFnnGvbbQozgLV2wOcbRYNyRVB9/HVDJyMwOflTqrsYDYRYqIWSgqPwSDgZNQZf0JjDYhAHUujx1RhsO48MHizHdkTYGQHx/25REDqAu4xnjmAIwGpuWzarXL1eGp6YoKG5Gz7jJHd9jG2OeRjQvQKnNoUHwa1jBynnljXM0pRsB+g8dsDCJGgkONeMrQma3ODFdMZH8z0mLrjhNUIDEU6Id6pfyy1n/8xJiMk8IXqthhs+4yU/mKtdB2SiAjTgQN2ynS68AlXUk3Br4YU9f8HewbZ3q3srjZGJw9vj3gu3yCfrp2+oAMDSMEnCx+kONzzh3qxg91a4J0cBloe4JmyiACINoGv0fDiIc+7IgTa84YdHFv1TPB69b9od62O/IuHYFqyU4roLb5ip4E064kAbXvIJB6o4xJjqeU4Dp2SVFMBlMtLouOFvHpqipIRPqjHXtD89ROag1cMZHr4YAceBtnjG93bdBsbJxixBlANFLY7zsE4DxzvQoKBVgekUXuOFq3lhdH84YlbATkXfFxDOLe/mTbOQ7rEtmKhiooKTecpuywFv16vwdtyuB3t39Pe1JLQBjJy2rFEHM2QAoFq4ufPGbIM3Z4T+PwEX24j4Gu+f+zrFg0fpcoH6kJPB17/xuj7XKgVJOK4XXmEMa6Vdxr0sozcl+qA/VN3zIXvv+3dov22E05/6qZ/6nsIsjxrp5iFNF5i1JqxVQxtni6Wj4dHEeqi6uR/LFPG90Wvhse+3pysj4lVkewHOLeFUJzxsE9aasDVzuZYEJmDOJbwlRI+ffHeHamintBQhmWYA6WSomQaAsZaEsiWdgNzPL802ustNdLx0s4dvfxfu/I0+lhduOPueDrJ33o5L7dHEbjVhE4JMNVyLiQVzLvHyrQBSnYLb0sdk8NwIgVkg3MDuKWAlf24163066xtkpNrWPTPWf9oIVJ3oqVZEsLXdg+MEVLJ7EyOxEqERI7J5gieinpYONIYBIDx2V8ZN4dF4bS3hoc27w7aUMKHiFZ/wUTqpxfz4bNGd1UKBbrl6HPzeLNjbeoWtZbznK7wv6l17ZIFRQyPCqWQ0IdxhRmmM/8O1ckrepHu85NMuDj8RIiiUiLCKAsiTzd9LwqRb2TwMgG8OB9u8JqrYJAUw+GJ6D0Bd700IJ8k48IpjW5BqQ2mPR0Y3tr7wex88ZKpeCH2PKxjHtuBNOmKmhoWAmSjGO7UVJ0lAfotNcg+pWL8TBNd8xsf8oPc4hHD9PpPd93SxHo+N0a870eN7aoZ8PTtmzISpADZRb8PR1ruTTDjZPTrQ+zjd4YY2vOQNEwGTffdsIeng88hk3qUr5ejwhgOvuxCOzy3fnDzL5X09hDfmJDOOF3MbQHgaPKxx4A0v00OAs2/VF+H5mqhgk4xrPuOVkQQmKgFujtJDiTXmG+OuLlgNcE9csRhoBAw4Gbn9SHPMjz5v+rwtST0ikwHMs3lU3q5X+Mr965hjmwGJ2jTUct7yLmTcbE3icc0WUjJ7G0CGWOicRLNIRkPRf/F1ZPQKw/5/nDrD+h9h4d2ajtg7PTzvYRkAev0C9VwM62X82HFczFuSjArANrEujF9UAhcCbwQqAiofQkSP2//0bJcPNd7QHwR04zrXjGOZcV8WtKQI1rkepam3w7kaxzLbJqkL3NYSziXj9rRgzhVzLhcLmQKGtZrFyuqaqo1xWicQAaVqjPlhe5ylcDOt6q7jpKDIQJJ7PKqdqzRGa4TWOKzuUhKaZ1l4Gi1gIZKLyYEhLmfWuGSd9A5AdsRL6mMYn2H4zL0e/scR3NgL0QpBEoNT6y+YCGrzVFtRr8iFexx4bN3VqvdOTgBltRqIBUii7sXxK2Oqq4MKmBvS+9j2L2uMT/KPOuoXYVTz+oxepki79UXDv2v9IssSIhYFeIX3pNTBG1OEca7Ksp+oYeF9qHDcxL0xHr+0bJbhBCDhjJXUZewL8207YOENE004Abv0U38OVTgAoj+PA2+x6TRhbKTvjbvZExGm8FIQKgQHAqo0VLiV/Ki7aFDQNHk4ArCsF7N0n9ioN7OyRm6LkjH7/GzCuK9KFgc0dZgtZu7v4rllLNy9EMpVqFgIOBBhIkYTwQbBsWXcy4Rv1RcD8dUAE2/4ON2Z5V7jHvoz0TYCNGCfPqv30I/ZRHAyZvKYNbPBAZ17DO1coB6Ck4z37YBjW/CN8moYN/3bbbvCRno/HgJyUu9JJnyjvMIqOTwTt/WAa17xMp0AAPe8WNhlC+/OybKwXvIDGC2Im4kaDrLhQOuOvOsej1ObjIMi4eVzPstMFRUS3qG39RoAcJNWJAhm2rAal2YjBVv3bYnzbpLi+a5NCfqZkpGyG5qNZSNGtmSEzA1MKxYhPBifyMN6GqrU4zSUM0WKehPNbnTgcd4m1MqRISfNvLPuYeBhDWnQLL6RwEkANlIvtXsGhrU7OGMWvujrvU28PBiUBEvxt2u7XTqeO+ERiAnPrp+70p434q9bUqOsedjevSA+8eOz/j0P80vC0y/5B9pnF3wUAQ2kvia6uD6UCbdFGeMtaZilgYLh71yDU1ErfDJewlYTHraM03mCQL0Y3vylL025IeouF5xrQqmMbTX3n5k5jngBmPXe8HBQhO1ck5FoKmJaF41QK6NWRtmSusTcIi+8A1sAYrP1zdNTreLBm7UvWdS54STmIb870rBGEDC6/cj+I3Y+R8t2ffUYMCCClglp8HzXwUIV7harCOl89Q0PEgBFGms/2UGldSMpKVX78AQap8vfR4thuId4seRxKvLoQfGv7TRD+vjHy86i+iez2sXEDY1Zu2hM9NBdcTDZGGdSUnMx8DFamBv4EQHS02ovPQnuRp+oYRHCgSqOpq/wllcsrCTfJgrE1WOnxGq6AIDOkfBFN/ojjESCDYTJQMNEDNfHAGxzte42NNWsME0LBR2CTfYegYOBGGZN1+QBcDU0JYOi4WRZNEyda6XHqNFQhHG7LSgt4TqvQTYHgAfLHnuoE67S9ijl9ECEAyVMlHCUDVUE9zLhbbvGJ/VFEG29vcERX8zvcKD62GMCAhPF/+v4aT82tFijGxCToYpgw95z5OEVzwZSfk8Pc+n3OIDAbT3gth3wrlwHr8FDHrUR7rHPFqwg3NYrnGTC17dXOLUJD1U9weeW8So/oNn1D3SFlt/vsl08RHLDZ8tkUg9QhBBZj7ltB+WzGUAojZUXQZ2LkqC/qwdESdSbJNy2A5ga3vARByq45qI7nn0XAN7LIZ6Pe84aMW4NhFaumEg3Ub23FOTqJZfgJTUQzqvuByf77ju+AkOQWcHRg2nkOPBotl6XmrCuCa2mWHOaaQGJvffEphtUOuAYU/8BgDeyz+0DUsOmXZkhZUYjrQPfwt8VQkey0PXdecwyxIu5ON7w/QKxrolx1yLV99KT4WssbO1zENGMazfuF74Heag+AS0BLRPocWT0g+0zCz4IsE2SsK4ZNTFK1UW1COM4rXiR1WU3WtcPZTIiqLrM7s6ziVwRzucJ6/0MaYQlV9xvMzIpAm8gnEvWc2/6Um9VY3zaIXugJEhJFAlXRsoNzIJMPcXSuSejZ8U3AnfJeexvzK64jAWOqcYBPEYsUcgmlWjmS5CRsPdgPDW+vsnu3HYOWvpGAxKQkZSmqSKlhilXy3xhlKrpw8wS9ytCmHPBnGrEQ92bRNyAltRCAIHMHU2AEqGupY+PzwFyUmofNwDdSvAu21j62FAZvCQ+R/xFd+xi6WK7dDRCD780AprodRnQrJgLdD94PZgbrvOKV/mMhTU1OdKvwWbNZXyrvjBXdM8oAXrGxQ2fkYwU6RwLQDeATTLe1wPu6iG8a5EBNrwL/v/iwA8GQKC/37clNi63ZF+mB9zQGtyGMc0yDQMU8X/Zu+CrMA68YTarN+L6Mcn1XdPN10jZ7Qrfqi9wVw84Gnnc221ZsNa8yw7zNPfMDS+X1QwMtnHQjJIby/Y4iWCTgoqC28Y4mkegCuNtvcZdPQTXJKFhm5ISHduEW+7suUshssvnlezvJ8nB0XDuiKf21pH8aVwez+Lwc12mV68GQJQzVDGZxa5jTdhkiTH3lOeDhWWqaNqsg4OTTJG2W+18i83NyMqhnjHzA+n9jr/j3piTTJhIwcCBNjST0T7RFKGMcXxSADE2b2DFm+mIazoPfBMeUpU794VJ0MyD583nQhPGph9o9mKdUFrCA6khuPAU4Hwz4HXrYo/cMBtQ8YSEtXZ+HgC9rr3vIlBvpxCk0M6rIBbWDeBhYWGysK8Ma6nzxdqkXt5dmJctlOxhDECBQjZAEbw8/a6vWQE6kl3LHbKkhpzLLoz7AVXqOkje3MsxNpIARWGYTe2xwQfr5+OgwAfbZxZ8ALZfNAtLeKgCanH7BJm5IFtopQljM66GE39O62TfVVVNnBglpUgfvS9zD43YeTfTpaiVdzE+CgCiP01IM0VHwpFtBH5Ob7pgmldAhpjgOClkABnjOAQk9WPs30Iaz8s6kZykqfG5J9xfw6YbLcCMARd5fCAnQUoNKemCPyVdGraqi8m6aqiKuW8RRJoRs7u8gQgiaOYJ9AUHdVEythBSrf2l9/BII4aQxWUEQE0G2uwC/v8Czf7ZKNyCIIoXdOTAuOOHtsEiIAElshceHSRClMx7+XyGPjABV2nDTT7jZerZP5PxH6qJRn21vMZvnj+HCvXYjZtbZk0F9M3GQYDH6t3qva2HIOBdhrk0M8X+3+53nI8V3N3sbcJtO+BYF7zOx8hOSCS7tE+9j+4xPLUZ36ovDCR5aEVwaFsQWX0D1r4ZedMsfSe5+r1oaEA9RnGNOuGhaJaJh/XYUmszNRwutGfUa9Q0k8S8MmfRcNAn7RBkyQYO4PF28+wWPe/7fMCJpl2WjvNCOtjQa46bvqcRn2TC23qNhGYehc6TaMJ4V69wrB20OXhcDFh41s01nwMU+jNQD1m/Xw1JZCOQKonXyZ4A8CYdgzB83xa85evwomi4o9h3S3A8HLi95HXnhdvAlkWjYZSYj8aXCUIvNeurAbUxrRaMGRve8HFP1h0AR42UWEESTfMdwWeAAyN0NRLj2DEKesi3cAIyIu28CEeY7ibn6GtpKpngHkPPgo0Qua3JMmoTjS3Wb/V4OPAID7R7qIeQcqSvXi7TCarW7EZUx+zabD0jUF/vmiZSNNOHEuegCAGiAEOaGWduO1XNkozrm/HrQCaOM8MsHpWoJIJM0gn9gyEn+Yl95wPtMws+Gnv6KJkCp+Y4Mze0VLHWhPfnw6PvudfC+RplS+qlOCedOKzu8tN5inCMH7/VFICjNcJ2Uglw1+AAlFzE5mZjEuTcMGeNL+YBxRfjkDgIWU1ILLuMeFIXnQAaD3Qi0rixRVzNJlN4A9A1s5p+H86M5hFEjIjXUOuohudgB9AXx2KA6j0xtxqrNT/PBa8OZyy5YEkXfJmiL+x9PQRQqAfGnFQHxF2GTIj7F9GwE6eqnqPc+SQAMM9FwYp1tTXGSWbUgt0LTOgeDgD28tu/DcENaZNAltaJtQOfpgMvd4vai00G7qpaOxEicuAyPq+BwhFpfxYrD/LcsKl+nO5wOGzhQfC4+ag5s0nCsfRNyjemzRj8d3VRi65mnIrGrD0Uli7CYDr+Coq/Xa7Vss3vFWRw2xH7Tph24k6AEj71HG3nEenaE5NZuTrGumEoSfFtu96Rv79VNdU2VCjRIgXS++DX8nTeQyqYk6baZ7NYtbSByqt/frnD66zpw255r2CcpJN2X/KKl6xk02NbcM2rCv+l7j0CgNt2hWnIANrseH+ODRShq8/n97oBE4dHy9+NA294k44AjjEW+v1Lvk/3aunY9mwQ9xCd2oz7NsOzTBzcfTx/K7JqDlRxTXWnuno0jZO3TT0TkWqaj/go3+FNug9P161cYTXPBtAzhlynZczE6lyMHCJnrr/BbcapzdjIhB7R9TYY6gl0HRL3qmzmATpJB31jyrqf59yU9+fPK1PDnMou5F4bo+QNa9KQPENUIr1OOJeMJsAndK2lICxl+1QmHLcJx/MUXm1xb+HGGnp2HkfE4STWZtdZEhbIIrvQiD104+TZWt5MNIxs7fH1OYlGp7IrMCMAwA68uJFJpKR8YBc6CSOWnL8h/RggPCJdaRWACNqEWAd97RWCruECkBjoKIgwEpn45eh1+W7aZxZ8RAzMwhQNACdEGMQ19kcvCKCkUPcu1MbqLRnJgQDQCLUkbGZxNwcbm4ZZ2DZBWdWyFgaQBC1rRDcyLc1aTwPwiEsI7X6qIWgHL8QWmXNg8ESKUmxudsG4xAhQRMMCSjzqSPcS0dKwSUaoRbCX4BWCOFI2IANoX6dUcTVtqnJqJLJz0pRkCIxkpeen1FAyh5vfN0HX1WDPeUcHc4lbaGQQgJyqSoCnqiz2yjjTY5+esIBdLZCHe2rDugBY4ZIu+CPEOua1v6SjkSaG53xqUeEO9uzZCHdw48fTwKlYeDNCZw+Eugfh2sSdfDO5bQesprXhYkoABou5i7A1UGgeeDkBFzrqYnkS7wYP81yE8FBnnNIUC//Mm1r2zu9AF3RyMHRqU7xnE1csVLr6pWXKNCGA1BuWwEowNE6Dp6CuklX3BEDKd1AZ73VnzY8tvByWlbYkTZkt1NDib+opepFOxjPoL8i4gR2oYvINjzVd1UmSowXqYz8T21jkECT0MJmH0jbJSCJGqKQAaZ7K6ummPHgCuveke6vS7qUe+6ICWSdaMZEST+9lsVIHypl4ySs+4oKZCBMYTEoI30jQWr04X4qQjuqCrDjQZllCtPO0VPJQkhJyT9Ln4pj+3cmxvdzCJgmrKCG0H8cmANlLB3hIpF87B9AZQZqLNBbzbvs8L06cdq9JUzDumhzZ5sipTkoCb7ovPGxdt8OVmM9b1j2gJrSiayiRhMcjSlZ4qOSpELcBgDhmMPIG7BHrVBiKw54C7sKSYYA29YBHWD2AhoS0gq/lj5TBx+/4ZepFHwKAQAmWu4NVeXr08AbwaIPnl/CBWfx0+8yCD6qdcOoIUBpQtoQjFsxTFyjyzBTVybAXGuZufqpVQj2bFgIb0BAFNlKHXPundPCFcDnEndjXeR9Ad6dmk90GgFbTXtfCwi8xCcbkDunzC6KhAYsCQFit+TjWAFL/wP5NgFCLXTQyPzx64ZN/0MZwGd8I4+AxyGNqPSTlQ7Kxuv2g7sra1CVahXA8z5pSXCylmPQapaSwOGMc2T0g6vmIhWSq6gY9pccF3wRhaTQj4Nak3iBx3ROBXRshFOYLCpUBvfs9jf+fpD/1om5I59u0SQALTQGWrREgoEUc37MKri83SHTrvMe8eefuH/89tgWflBf4H/Ia3zy/iFh15rZT1Hww0nW2bIAxhVVj8ytuaMU1n/Gl3DcDb06MdJ7CqD/CwwZ26QnR7/b7uLnwovye6RNMqLgxToV7DI5tiYwG3WiyAgtaLXPBBNwIAbbWmjAzY2INs1QhVFKvS4Lghlsnvtpm2mrFJhpecHXMZhvoi3TCD+TbSGWtwlFXxTkq1b574A0fpTvMcL0Jxhs+BihTj8SqgGdYyy9FINswbvp3gqdZnzzbRRZ8q7yI7JKJ3lt6rd73JkCD4D5SoxNOkvGN+hL3bcE3yku8q9f4H+trvEhnfJTv8bbqMzvwiglVU23bhJPMSFDPWKKGA1YDoad49i6r/kl9gXflZuc5YpLuQWnYzV8P7fi8Uo+mcWJAPVUXmz5LC48dq4bkzjX3ec0NjWkPrIvKJEzGN/MEAtducm/GuSQQVPhwLRnn0xR/cw+nFCPHB5HUHpCDjXVYgwbvuB8TW4Wg7yObbeLU/+5rrg2eft35G+6C8GNHL68XmLO1dBdmHvuFwVPixpkZWgqIBiVnBxFeN4bNmG1i/aEQn/T/JwMuozH23bTPLvjwhzY+TwMJtTBq0jQovtS0sOaTsZ/solWNg9XqrmndmELsBegs5gvyo/flEfHwU5qCJMHmLGXnfDyBmneDMLj4aTwOj4+NiTKga3erifTJFcjYEDr5W9Au7sfQ+6WIGqCbSxnio37uEZwpudEWV+npxeNzcVn1WiU4IUBDJc3WkNSPj5RcYHePGMYm4pVuZoyPKb7TAZ9718g9ROwv2TgOiDgqyF5admAjxrvpvJ/QnxjeRNegmKia4JWNo/1bI6ukX9iJmU0IK7pbOkFwz4vGsofrdNKpcSOQ+/OTPTdJ+ySWEVLtRzStd8jw2EwWf+MzNmiNlPH7nlY7kW6qvpF2MEUR1gmehJFZF9L6RvdScS9z7zc1tEG22+9rbL5Bu0Xsfx+t5QS9n4UYB3Ipd4G7GdmeSRric16bxoW7XORLpei7JoiLqb2yqrJVfeNDWErH9SVJjKePJagDEE9P9ucNIMbtZHwY52vcWlXXkQPShFGJcBL1/nk2zb1971v1RdTN+aTcqLIzGk48YeEJ9+ZZq6a90ez7IAUBocJ6sTS4FHuqsgsn9rnL8eMhuFFSfvcsQTGucX4z5DZBePmct+H6SyyavlqtYq5KKjC2qmvTxFrXS3kdHGKUnn0YhS9NZ0nXFwzWPeCK0I/I/xiOg62zPC5CfgB1T4iDB1+ThneRzCjydTr+Pqa4Bqft4vq+NDmo4XGQpXNLLIYzluXYGVzRGey8Nx4e2vVrODYc7e49+S7bZxZ88Cq2KbgeAwJoNNEQiQggU8Gca4ANz8munhVhE0rmwa1rG1bbEtYyqGP6g/VNkHp4wOuqtMZAMXBT1XIvVcXEHuqEKRZQ9XicnURuC79KhXNHzTYx2jwgXGtkE4XPg3YFusUN+GZrE4zREbS9MGOqbnx/N6lFvyN2gxv1yWohlJw1w8ULXzVjh9+eFqxbVkCQW0xMMgGxUhnJdDwyN2AqSInRWkOxEJdUCvl0ACGtvnEDc8bDebZnQ1qieuUAg57vzqu9GCOfZXjW1GDxWuoxTiBCNiMbXDNwngAgbr1YTFcOAHIDJa0QzNzC83FbDpHSqo+CcCS1KhM33DYJMOGeBJ0ze9d8bO4kmNCwBclxH6aYjQ/hWSG+cS+mZaPhGP3dScCbJHyrvoi4vrrgC15y1QgVMSZoxVNPkW1oqCIYU2036EZa0SOHEwQHrpigOiHJN/sLZdhNBEdpuK/qaj+3CQlaIC9ZYUgvm+CckTWKO3bV4OIhosHroi5/wTUnHChjoQnHtuIsBd+oV/hWu8G7eoPbesBX11cokkLt+CQTJilxzRtU9abY70CXIJ+dRGvX93BCcBkAHJsKft22Gfcyh5iXNyfg7mv0SOhpnGTCu3KNb5drfH66w+fzbfBavlpfYy3JwhW9emtCi5RW1/fwLKKHNuPrmxZVe8fX+Cjf7UKAH2XVOflieh8gClDAd5ZejbkS42VSBddvFy0376HAe8v2cZ6Jp+++9LRdG6OJC1h0zrueiZOrfY6fW8Z9WfDt9UqLg1p6teSKJD1RQKseZ5NVMJ2mVAJkbDVh2zJEYO/qACjcqGzYJwNYlpv4Jj7uu2Le4awGCOXWvauR1m+WkXtqR+AxeCmiYu2QgODpukFOHXlsNJTQGA1YN8TsRxJhvyBaHyY17C6lHfzQR0KVF46A3emq/rSE32HZLkAPP3hzD0h1D8hgdTZXmDNb6BLWOYNHYGYnPbaM+aKCIPrfBXuvhwgijri2bHHoTvZzzoML1jQjt4YXxS10vrgWEOmz2m88aTWMx+7vE/tJ/OhWLo/vKP2yOa/FWxHehWGIYOQrK8pHHWz1NFsd8E0sb1wovE3uAXKgB1HLSdo+dNaCJNqR/0i12QGGSwAiurAEwSvQ/YDaP9QuXzqzcnjSNOuUlTTrp6iy5194iuWG7rk4yYR7mXeS3B7KcOubzf0MdPKhx8Uj/BFhRkHjGhoZ3pgkMgBYejkBV0sFEJZ8oxXAio0qKlXdeJA+qOJZoamso2CWE/xmtPiea4Z4C/AC85ZILwbXeQH9vkZQATwObfYfK/xGHBZ8E73WhoqzFNxLGwCAFli7L1oRdmaK+ikJDe+Nr+HqmwAwC4zHwOHur+YRci9JQsNNPLeKe8k4Nqur0q5w3+bgT/iz8OJn/qyZlLjbVTp7QTUnmyYIbi2FdiR/6jGefvw4TdXl98/GTVKPx4Z1uH4yb85Te4nzMjyMciDT07Bn4Pc0yqOPwM0rGYOqCeiNxfKMmGsgyp+xayjt7kUIaAxwi/Woayqx6Y6oR0hFHik8r77+ECF0m8IjK51cHm1cHy88Du6WduMyuGI+T3deBzyqzvBkc5eEoIfCLwHA5Xp3sfb58b6m7vZC91KIb2qf1pXxexfeHd+bfVv9neD5cEEvstQmaeaaN0sTQmgN2KzmyJRqEBpbE7TqehqWReKxMnbgQXv30RgCyTorxwnoBEyC8RFIkLJa+FtNuNvmnUu7GjHq/WlR8bI1R7pwlFoG+qS4nFSAhQ8E7QAllZbOLoa4+wyRteGllHe+NMv8iGv5i5EeT6Kw7h2YFYK0hPaCkOzF6hV8GYepoHDPUonIjhDmueAwabrmlGosBu9PjFoTauEurgaAnL/iqW0rxb24F0rK4PVwEEJAPQxvm/T8endVciE0f6YRQ7WxSiadPXrGgPA0jYJt8SJnnYPTXDQrx/7spNmFa6RNMjVstmnctwUnzDjxhG+VF/hmefWI2OltJK2OGRBMgnf1Cl9fX+HcMl5PD1EIy8mYrvboWQEHK7rm2QGbMN5u17GZNSG8yOdO2qQtOA0qAtVF0mzQ4CqaqqCZcJIZB1qjJspExeqNqEdloq79cLJ7PknXPPlqeY1vb9d4aDPuyhxjqJ4cxqlqRsprK17ogGOrqio8alm4U+htu8J1u0WykmnfsKJs/+/1B3DbDvjm9hIPVUULAeUIqeDU78FV2vA6PQR/wzd1T4EeC5WFHLdkvKtXuOYV/8fl65io4IZW3MuM23qFt1XTXC/Jpdd81uq9pgTrZFZXHQUQxNhpGF8PG7H0uXuwwnJep2Yx+fBD2/AJbvB2u8LW9J7nQ9cMWSWHRLoLet3WK4xVdv0ex6ybip7aqvNT3wE/10s+xd8cZN42xv9j+0Hc8BkfpV7fyNNzj20JgOIaJ4kUOC+J8OpwxtYYpy2bmq+Cqc4Za6iN8LDlqDfl8gnuwS6m2dEa617hnokRWHhI1Z0WZoCJeVzF18zCQNMyEU9u4uMaT07e7OvL6L3eeRw2gCsBxbzgY/hk3OQNSHhEVAidBGo/dNG3UQ+KGoEfbE9J0uUIgB4XHoGNKD+Oyt5T851AzGX7zIKPXYxrtNyfqK/hSFezVC7/iO4CI2BHUgjvw7ihqYV8Gdd68v+hqLlW82wIh8VWBiTeLF9cHHiMYOCir+HKu7xmhFWwT+Eaz+Po1yd6GybdJbgZkfJwX4qw3cOgX/JqrcDekxOeDZYeqzQQkkgCeGSz4j6txXOLvtuzISWBdbeIHzZk+PicaLR7bOGCxIUVQMP4Di9+jOFTL9N4XnfNDu2pBXis9gnAPByb6SsosNAiZ3WX4TLOIy1Jr+JVbiFulsIN6Div0Nj2NKShNmGs/HSdlCZKBPbshCIJKFAvojCOXMz9XbDmtCsQ5mEaDxN8wwDUqU24Tme85JOlc+pxJ0w4DtkegGdPdJ2Re5P+PrcprHK3dqtQyMU79yNzRbZ09inVAH1puIb3deSoaKbIHGPt6ZnjuBQRK2ApuMPyiIB75CX0Vy7b1jLelSvUxFZOHqi2cTO10MToxfj03C4o581Fvrwo3z0tveAfuofHQ3PJgOWEshOlc++PEzl9voxL4Mgr8nG5s7ongBbbO2GKIoLVeRwGPEbNjb2nQjMFR5Gyy/fBxzzGz7wdDjw26dlcHnrzpILx7Ru1mABb3uyzOlyye2Oha7GQVdh+1K2LtVG63IJc/tFvZNyEab/GDCDA3QSCC4L7B1p4ZiOEM5xz9MLgA+ca19IxbGTH9v1hX8l2Jyswfsf20Edxge/Gm3PRPrPggyrARX+iNHEDhDhIfl0bQpEtgAhrRCli+346MlqGaj2Q7D0PQAc6/v9E5gHRh0ZsHhcATlisjUCi119LwpaNZQ2vf2KCYvZwWyPI2YSxngiFUDPNiqwIOOqYhJUO88j4zEDcQxQS8lTQQpFOBSBQs8cLqVBH2uPEtDgjb0CdAOSeBgug66FIJ215SMazEbYta8ppqlhSwSFtKsNMSRdKG0sh6qGU0fJwS+HRAFk/LUwlk74lCpa0z4BZAIIgkcZ5PXV7sC6cA7JTkPVjLxcH+xxF6/CUbGnCqamhZIdNnoIa08k3DMLEBR+lO/xAusUfxFeD9e+L7ZjV4l6Bc5vwzsq8MxQ0LKwbUxGtwnxXFmRLgfXQSrE032OZgngXmitQXsmGBBY9Z628UxcFgFf5tekyrBHbd5LnWLl5E8bH0z0wG2eCKr62vQlg0kC4HgqZjcRJpoZ35TrUWhNphen7OuNUJhRhvJjOmLngJp9tg1U+TDsQDqmE1+ZNOsY1TjLhq+WlPQMOroVvkg9N68XcGL8kqgFDRanet6t4fue6Fz97kVfMpufiqaVeeZdJInSjqbAnfMz3ca++GX8o1XYknL5HxX2bwXQVAO19u+pEWWgY5k3qlYI9dfvUJnyzvFSdkqqgK5OGCnkXHjGgaOGdb5oOy+enO/X6CGPiop4gGCgiBIA8twnHOmNtOUCC9qsGSHqdjwPheNNMGgPTp6baHvdtMT2Qnsp7apoi62JznmorAJIlBDRxzyvFeDZbo51kPeWKHMcwysb7sC9drKlAAArnoQXICT6hrgk9Y67PD92j8LQ3wLwXuyXO1m66MGpkVnVlGomoYhcewQ7QPb+tr33Ox3CVVKrGGxkFxqT3x09NwUkcOu/7hQAQgVTlywk/vVx/p/bZBR9NsNsMfNArVFvfj7vwhLhFGpkrsYGPB/nD666vcZJE6pGDEEOqLvkdpe7dS5HUGzDqWTi7urnn40OhlZgwNHbJ+qk/NAYJSRAl4d2y93k4GhYGcCJEFzyH7iWAeEot+ng4MAIUdOWGxPrj/I3MDWiMSgIeZpzfay2MMhkvhLvFErd1GXv0fkl/Xo88M7sxof5dv9fxcxvo3YssHSiOYa6QaB+9JoPHZPx+R3J6fKsUonTMDSlfaCo0z7DQeXHDK274bGGIvgnVgS/RNQ8SViRoye/JNEN8w58AmEw2tJDWrqqsXS/mn2dTCKM0zZBBy+ElcRl4zciRqOEB9BAAG9NNORi9JahXi0Urjfp1Nr+vJx7iZCviGC7QzA3bPOxeXNfB3yu38P2YyIQZLOrq7kEAmy1v7rXR7A1P5WUjaGohPM+WAIDMNcbCrfjKFO8Xk+DK6upcpzUAIVg382teTTm0ht7HfOHtuGz14j1aoWGto2ioyJVsHSwo72ILT0gIgpECANUlWXBbDwGKzibK5gBhbRnHOuvzYMT5/bl65pQDpsiCAWOVHHwUJbPOj4DrU/falXylE6yH0FFCw4audeMaNoCFVaSDCyblDSVSD4cbfE81/Rt2IAWAGqkyLLyy/w4EqmHUpK8bEULxr1iq68U6JF4rawQ3ceGxc+jr3u6Yx+PXp/qlYfZo+XtEzxivd+E06XthM2NsBBXj5cYvBRhxQPO4W5/WPrPgI536Qh950AzlbmwJbWU084A4MvURFSGrKkiqydAo8pY7yNinWu4mk7nXyEEO6WeekRETqgFIgjoJ1injwYSxxrzzUpTfEFVrzWq/8H2Ctq6rIaNXxtNA0a10sRpHVLrHgxgWLrK5Xi9EYbh/H2JeAoe6LFrT6RLsJUGeK+ZcMXHFnCoyKX+gNMbtuoTYWwi1rRnb0eLUs7oixDbWAGQjaXQMMY01CAT6zMbicCNIFPSsHHvhI9UMNj6Do4qggJQuvOWeSRTHuofI8Q1fUHMHToysGsNmS7PNVvXXF3EXCEukxeW+mN/iDZ/xhdSQQBGaqBCk4e1mEBo2VKw4yz2qCG5FSY2f1Gt8q77AV7bP4SQZSy1R1Xmipox/kyh3zodOMYpndLsh6lq8yg/4eLrHdTrHpslG6nQ3e41zdGvZvRmV9zVHnOg41is5pBLcgYkKXqVTkGs17LLYZuOxfeMykFq5D2XCi+msAAD7TW28P+/XqJq6ScKcjsqrEE0n/Zq8iWJra8tIaYvwzgLgRTqHt8c3QfcKeFjjc/neNFvOMVbat65Sqloha2QtAdgVl/M6MK6J4s09YMoRucJvnj8XNW+OdcYdHwLYONH0k3qDreUAjg42vn5+GWCjiIppOWh7vx1wNi7NVdrC83TNKyaueJlOAZ7iFUQXjTtJxje3F/hkvcFtWXCqE2YumLnio6nznibWzCH1liDEx7z+j79XPr9ui0r9+z34/PNaUVrWQsOxvoGtSCi1z/GUdA47D6RUjizJVpXMTgxk04satZ785W+iUgBY2Tyhe8NIvCz9YLS516HZOt3XpT24Ce+rG5gXoXQSaMrsaKdV7EDKfs0SyGxfJN/X0PkkDgwcHJE88uySgyDRiIMkW3I9u1IQqcK6D1mNmQL9gPEY6HxK+8yCDw/FkgCoJq7lFq0MoiwAINSr7o0TZPBmBGnIU08NUBC5l4P69XYdGb7ngMFRok1YNEGrWvhOYxYj0r6w9Ic+e9vpbqRhorhHYOQ7DN6OCMsYQUisSBp8rDw9a5xk/ncPTVT3EuzvNyacW3/mki7EUdwvMnhGa4Is1Za79TqqbmZuaFM11Vp+bEXQEE0cPSLAo5irA5XwXgygQfyl8aGmYVzHccjorsQPNcOMMo67QEWIAM22YtmNgxeFA3o2AwDLjNATNfENSa03p86NJe0ZAIgwiaCay3u6QFBMpvzpvBx0bweAgQfS51wRDbFMXHFsnVDYiKzfxazchkS9Ng1DAcPC0yOQ4ZasbyIKNjpB8obPmFCj2qlvZCdoBtDCj2V+3ds2enD8ngFoXY6mCqQMsfNsJt2+WWXTx1wD15FgSFTO1YKUCa7TUqGF6iZ7EElaKLt61VZXL71smr1TcesAFLIDGlU4ZMQ9TTZ52NIyf26bFg98W657SIj0/mbTSonrNc3cCa9PSxFmAS70eIY5gKaquh460o1dLfZjm8GUBwn0zknqz0G03AK63LlzntIQGtJ7TjE2x7bgBOXBjJkx03BfI49krJcVYnNDH0YVX0Bfb+YWSYTuGZFmSqOMzv/wNa+ZgShqqEgh3XuKgYuRPmX7EoAI+6rAoq3Jo2EERAi8f077tfzCS3H5b3jIh2c+rumX18P4v2LG7iCvEN/3c5iR5U6aRhTr5y58Hd/rtV1CSr496az5YPvMgo8699HnzRCoe/V80Bg9E8KzWrwNAAFA51BUaNGw1MxKVuBBJlQgZjqTm9DjOZ17cokljHR6XjMwA0wVzVC0q+b1gBp25x3DLSFYNfaZDGiNs9FjevZCSFaxK8l7kTExRN3JnPYPi46lb+SDl0D/3sEHs6A2wqlknJG7VwdaWK6YSA8A07oQYCnIpr0yLhiZGq7mDTk1LfRXRBekRgF0PM25uy+GjvvYG9LW6pHqNQKguevDCxkKsOYluZQmFhbziEnP/rEaOxHH3YVu7GewclBSgMZ6YwulhQS8CJxrUGgxt4R3TXBv+g2+8O7kuNHwkjcwgINdfiKgoVe5dXe7W+NXachIsM3UF2L3PACIzJHSWHVBREM+L9IZxzbjZTrhmlcszJhRdoXTknFGLsmizdzwYwZIFa0O+zI94GO+xzV71othYgD3jXFLWt5e72ENDss4jokbiiSszUIz5BtOw32ZA0iVxnEPn8v3eEkPIQam7vwUgILR03l1PFSrJ3MbUlqd+NktdPc4uFfgERFXFOqs5jFxr47zTVTeXPt+V5WXcVeV57CwpvQ+1CnGQWuZTFodOW1RL+bayt0nmnASxlmU9zMWKKxg9T7ARNhaRnGVV1FP5EkmsIWdHHidOZvA10j+7am+gBZPfJ11bN/kI25SijBMg97LGArchvEBgK+W1zrf2xYARfvdw2iXlcF3Rg6GfZOc+N7MIORI7/cimMdVN4/ghfB+pxSXQfAsvEZWc0srzEKANkv3fAqirEP3BECVkEeQ4X01Dl5bZJeNMuo37YjvGIwm98ZCuoCYG2W0X9MiBG39IdsDQAiw1LNm+rVa1uu7VlJ41L1InoujuZAlaDCC9RpcgfaYh/3B9pkFHwA8fbq38f+bojlNex2Agm++IwHTNlLnZzyygtEt7rBwoxOIQYeHbkg0/deRZqMQyyrVappYhkutPEipYyc2M25mZBuaXKJrWP99Qx7dBIZn9F0dwM14ChpuUyiqGUq289kMCA5rG3RPmtbAeTjP2KouzC4aBgClWhXIyJPnQT0QO6Lq6AEBeoG54rLl/uwe3cDQ9yBRKYiMF80dKBdjt/P4uMfCL0NWw2ZqGrqbWoAIVLLgB/Vr2NjAX66Ra2Qu2ZCUtxCHp8964bhP6gtc0xkbn2MzOja1fl27wjd51U7ouh+AbmhHWfC2XivJz1zxd3XZxdt9M/XxXluDpseaWmrrGiFeAPG9sBIwW8Z10nRShuA6KcHzhs8Rjhmt87EA3cG8Mq4vcZIJ3PRealMlWydXqmS7aV/UKxzbjCIq1PdQp+irV6fOVDFzNQ+Lzt1RaMzvRz0dKoR3ahPuaYnsDK834lwCL6V+ty0RGlxrjkwNb57V4URf9+Yw7HoXJFoNMZUAlMHRCA+gApoXBvReZ608694l1/XowmA3cX6v+OqegjEc9CKfwyvh/CAdn873KBfAVOfLFOdvQlgMrHiIdaKKyTy68bvNj5OkCNcAWosmOF6095IA/Xet79KrIetr1ImqB97wrl71+kVDfz3Um42Llk1fKBng2AyMqP5Sju94CFw9ELqWe6HK4AgKxd6hIpdDiqvXULE9JozCS3PfP7M1KMLBowSP/83LCgkgXtMFA/C4WBJjTdvFS2Kiap/d5kqi92F7AzV5BIp2npUAMQaQoOudEEzHaTgWo1FLfQ3eywx9avvsgo8xRiaELoZin7PoRu6D5puBu+JXHlxZAkz6tDXNivbkTFB3hTlYubCQQQDNLa4XnBLb1KSpcukmQCkpqiJGNoep5YUe/xDziwqsA2oF0Ce5o9GQ+kU/h/QSzpcTySeD8Fj+2CaKaYLIuIkCkOYeIv2pG6O1CStNmOaisVTLbinVCve1bpGMZxsJgi4C5IuIWyTr1NTFtyYDEsNzHrw4ANTbUKgrvvpa4XUIUh8ncquCLS45PG991DYOC0BTQ56r8jsMMLZqIkSje9TO3TJ2dXS83kKrGoZyl7dvcm6Rf728wg2fcZRziFl5KfsITUF2liDQNyugb3C+Md3VBbfbAcfS5cmPZY5MJP2ObQxWkKuJ1ntZslYD9c2+NMZ1Puy8KAur1+RVPnVOh4UNNgML7vJ+mU54kU4RWritV6HaeaANJ6tkCnQg5dLft1X5Bw91wt22xPXX1uvWaEXbfTrtVlMUD5tIs30mLlGPBtAUW9eLGFNVS0s41Ql36wKx+TpxRbEwmd6fAjwHdLOFt9wrc5U2TEb49ayYzBU/MGumiFchVm9A1+9wj5KLmI0hFPeWvK3XeFe1IrCqfM6hfVEbI1n14ZNkLLzhGj2byDkTnk7s47i2FHVO3KvkHC73ShRhZGrIrEJz13kFCMjmefNqzT63b7dDeKIc2G6SMKFiVNyN19i4PT4Wnt3l7UArGpPNzXkHlhQgpqhIm8wjdCXDvaWM4zrpfLeSDtuWNKyy6i65q2nl6417GWyd9X8liwIPywyUwegB3BOAYe2WndegVwp34IDgV7CBH+clthndwCXsPCHh9b7kVvg5rT6Ve5Ili/Ee+z4hZoSHR3cEOATAMzob+vpHQJsGjHWBtdyLo3sNvuv2mQUfaW3gDftywP6/AiWe+s26F4HQEasMnwm6TK5vtu779Qc6kA77xewfT0stBDCBLGQD8x6ocqZdTpy4RN0rEtkjA1OFbWI4ADBQsPOIVO0fYfgcjortHjyDAxeW/tD/p+4pmlx8bv2JvHaCpuYllQ9n7lkAramMfR28OV7Z1SXVp1R7JsPQOfeagEz+3lB6pLF536xYEjB4Lsz1aSR9dZMSlL8xGCJiwEM5OOgvveixrlQKgoKnNvAiDNiFJeLXb3hk6YxjLkK4H4AA4GEI5U8cSIuRNdYxWyVhQ495hxqqx/3rVVjD7knx4luZGxYpKGnbeZh0M+lAo8uQP14ZunZGw2zCXqrQa+XIhTEBeF+8rkg/hws/MQRJGo5QfoMDKA9z/H/WjwF01/s4NlvLuKsLjm2Oc89cojx6lDUf7mMs0uYu94QWJEm/RgXjtl0F50bDLcB52GRdoHA839aSAQpEtocXtnMJ+0xVs77QN2u9R0a2eihaeO4eKbcI18y24bpX5LKaryt8ek2Xk6h2SwPtNFw26EZ8khxEU1BDtXu9M/Dh6cQOLjz82eyex/RUNk+HA4+FS2T0RP8MlPk8VC+NehMS7bkg/szH8IuHDL3UgNd+uWwqsKfXv8XS57AZMWTzmUyXZa0qfnguKizmng7n3LmRpDeNJ0LoF8ar7SHkx4Zh2PsaAMbDGozgE+5rwQDiC3iEUPQPbbK9qkisa8Ld4OznsIXNNhry69s13WuPRuAKk5vo5yMxTsfo+fCwMg3X8zGq1JWxDQzFq+9gyYfT9q9Lr8p3ap9Z8MGrgDeAXIXYb0oQYYYQxDILP9DfpWfDJ9Cw0bqVG8CjDBkP2H+XqmlreP0P0gJkiHNI7PzmYYs0XycwPRXqifsyq124n8frsjhAEgcDQKDhXS0TR7yX7QkGUISLxn93gw84YZVIgUfONVJuvQuaJ89omwYXyTZzFyWbkmbJZG7mDegXclY6WX8oqe5HFPEjey5btxrixy4eiq92Dw17aeMAHkk6r8etHG7KkUkmiwx02XuBgQ+B73TCom5NV8odx22wHpqQeSEkCI2+2eqGtOINn6KQm7dNnIyqWR+37bAT43rXriMu71a+k1pv8hmLlIiRZ64DtyPh1PIuDfEyBdItXP8XAFZkbE29ChuAh7KgtKQZNLb5zqnio/kIFkGj/s55ZVp3sX9ru8FDm/F+OwQ4mlh5KqPHoDTdqOZU0QrvAMd3akyChYrWGhEVwDqaeJlnoDif4IwprPYmhCXt+zuOk4vleWXgo2jJ9iVREIaLMGbuKbzuQVhY9SxCMXZIsfYNWbkVvQhfhRbiS9KioNxEFQU9NKcbusr1O9H0mtbw1nim1epVYC2rxz1UiRtm6/dI3Mzc4CJuE6mnybN+vDlHpUIJuq7zonOGMHOJOeRjWm3u9xRqjvo5fkwUnrMxaWgGPjYbY1UBVkFJXQQ8tLlW5YecitZ1KZUjxBKVauueLxLCWx5+dlkGW+8DbJiRAwAew47MSSgocOO0uVE67FURsrV1R5LE+qQZPrqf8RjuZuncPzeWDGDsjNPRQ+99bUN/fTMa6ZDOK6nd+wLgIvuGetahr6cOmli1QsaED+Hh2N8Jng+Nf6GTH32Tzmbpj6jLSUBAR5/uxfOHX6jHo3ygTTo3RLuGrAkAsZjuPA2e1ut/MB6HNELdJFJ/I37oYi1PbPK0EtIDq7vNpdHNlScEmyAGkOx6YkDl0QQfXqyw/gVKloKCsyhQRP0F400R66MwDAsoaeG0aaqYc8HVvOli2ZRoWkvq6ceBaAC65HqYmx+5aFlrWwTFPCoA24IyjI0zzAMsSAchO0A2fMfwAgYv744sFQuDRFE6tQYYdKiRsk1JLV4Z+SjmFh0tklikhsYkmJNabB4zB1Qv4yWfcEMrJvgG1LNbDqQVV6+poAF4yRs2YVzzGce24CU/4CSzeQgSXPlxJAGqlW5et6FjrocwmwVdGqNRJwJfpQ0Ll9hsnKcAIDYMTd/VMATggKUGP8QFpUZej/9/5oYZKhDWhPEqPyiB0gi555bBkLgX3wBnEKoUJAMJzi2og4W9JC2W55wMr0/iAKIK40U64YbP8Z2zZca8mM7qzXDOQkOEcGLsIJiNPLmJip1d5xU3JjJ2lVwHpc/3hQs+l+/xJh0xU406LCGlD+dj6H2o6qqmHKveiynNtgXv6hXu6xIgwp/D4kRYLmiN8Em5QWls5FUOjtW55p1nxttlfSagqzKjdqAyccUdLzGPNJTTPVhsIGUMG2auBkp6NtSLpGPtnCKdHyr85p4P9/at9q9f08/rWkoaShE8bErEXXJR4cPGOG8Z65ZRaxdBhFB/jy8NwHHtNCsmSJW+mfoSHkaNux70x9edsRQDbZ2ouvMuu/EsowYTUK8taWBSAw5ZrFpjP6dMqiRNG1uBOel9YwkQ4OWdfG0HdyI+wQzp8OSMe5moUJoZ8QG8EnZcDs8SjXtzMHUZJv8O7bMLPtKwWdD+/3eN0b0Fg5vIC60Fm7h2K9s9CGSeBnFg4tZxdAJ9J7eHiHHiAcFDgBcsk0udjqEPDhxEQQVvhHTW3H9Mw1OzDRImbBQxNQDEUH0TYKjZsgceve/o1VodaPl3ncm96gStfn8+PrYRu6W0TAWHXHRxtmwET10bx4tIwzRjnRuXRM5oQQZjEjRyafYhj80nsLsExxfX9xwPozBC28QXAbqc//ZMJaFbOUCvxKg5lJCphWwzkYJIFUiDZlJt6GPjfXQ+zxg3BSyluJMjm1CQNpVQKnErY1rtwn1TvZZm2S33OPEpXPGf1Bc4tQm3rYuMtcFi1OF53B/A6EyCnfquelF0A7nmFddJLXRPm/Xz+6Z5Ng6Hp9a6fLbXEPEwwFhUL5kV69f7eLqPLBLdZA67kEwisZBIxcRDyQLzaGQDVkzN5Pt79eBtWCV9XA60mex7r0yb7J4BoG2EAte/eIJvY3MODZhs43wzHbFwwYt07joW1iaqeMmnyEjxc3qqrYdUfHze1uuoXOuF+fx+nAtzbhpOWB18YNtVQL4vS9SpaUKh47LuvGFk45IfAQ8AEWorVqritiiZ84Gn4Lg4qMmkzzSRAEM4KJ5fSyjonCDPfnGQCGg9GR+HhBbkWefnePquj0cdhBshhPNGaFk9qxGWqYxts1ovdl/krlFvl78DjzdNt/JxUe5iXIfk4mfU4CjDXuJrkgMPN/7Q1+W2GPF95BUKG/gYwQ71hc73PvjnCKBBrmkkgFfq1nMiOIZh1Nkp1WCWMKrJ9y73DPu1bH/tvJE+nE842j/YPsPgY5wsCMs3cqr9T6IbvzN9Y6L4GuSeECOcImvpY550eSRuysdhJ5B2ANPFx0wLZHRF+ebjoYF5mKD+APzlHtKzaOUAMy0D5QqxoVG10w/hILTRYod+HuJn0ieZXY+c5+CI3IBQD+vs+9Y9S9LHsxCkCloSsFn/QRi1mCeTYDms2LaEcuqZFtKAWjTmei45Qi/u8tzMOjlvWWviVCOAjRu59y0PQA4jGtdxabP0MWnoxQNtDL38hthYhSUzAhr7PjbN2mm+Lo1EXC+tTdiDDR9jmxC+qbtF7NkHD3WKdMtV0q6s+oG2yHBxcSol4tWhki1rCfWmRcjcPX1XFnz19GrYVPb/lgvr0fVZ3MIdj7+pM27SijdTwmYgBIRdlguAnZteh67X+fCsHu/fy3Sywnh7b8Ir1rLqXmrdSalKitQQgfM9dhlSBog83NSYcDASqguBvSvXu/TY66yCYYkaTnat3zx/Du/LAd9er7FWJXKO41GEQ3FzogrmgkUINfm4cXBAdPx4x8fZKAXhVTk7XY7eq9dug8fKORSeKusgbeGiXiEDRR4Wcd5Fnx+acfJQJ/VwEHZ8H8D1UFSwbateZE062ZTp0XdGoDFxxcxlp/zqacEPdYoQY5OEAkR2zbHMAR4m7iKFxzabIJ1nQLUh9VzDSS4Ed1cWnMtQz4jbULtFZQAceIwcFl9LQtU0DBtHA9TXjNGCZ+rqpJ6pQoOMge0/NFTZ5gLAo1O2NuxelTEjj9A3+fi7GjyU7N5GQmjrCtijQUln48wN6bputJOoBzd0nqxTkXbr5/bveVLFhUe8zRJ7R9yvf9dDMb4/+V7yXbbPLvjwm6DhGQX6Gw+0PznTF1a22ECHXHotWOP8ydQoiYCaBNJ8c6YdiKCG4JM48lS3FXVvi/dn3LB8ohIQ3BTAHn5XM20zgtgknhblVr+DLH/e/rtNIHezjRPTsPoFSsYOnQLDvCPsJmF3JXZBnvjTsDARgJws5r3mYWwQhNsqBG57l6+nTpZi7lOPxY6s8+gX9lbGBTG4eV2WQo4RAxDAYp9jaEZoNwT6XX8xB4IwgJ5a5sp+Izl4dH0NRpRPkWnY/BiCBxOo0boihK3myGRwQSzVbJD4/zfp2DfZgUfgrRnZ71hm+/0xN8I3x3FDcutRAKBxaGp4c1LjxD0DY7Z7GbNwRmLsqGUyeh48m+GGz/F9RtP6I/HdvtFpNkYO1c2Re+EbcPw/utT/KMfuGzmgnAv3PgAIq/q+Lni3XWGtWTMkSh+Dbl1zkFv9mhlaqK9SVzRthmgjfdc4OQpC8k4h1Y/3bKhLpdaQUPc6POhAcswcC68SuvBaMfDj3BPPOhnnTW3cyZiV9f21jdwJvmN/PF3WQYOnGSdSDpenwZaW1PtBPjco+EYPRRVnPaMKCSitKviyyyWRXYq2ez08U8ezdLy5V7U2Bomltwt6mj+AyGyU/h3xzSTWcgxrK/UwxrA4yuhFHBZDL74Zr0SDAhDqa874Ooqvs+NabNeJNYqVfI/WxcpiqfHq5HKxD4DAnm3nOkfJkxBsLygu0jlubNi38U++hoqtscMazMUBVBfr3N8jvuv2mQUfGipAT5McHjY1hCiKpzPxWdGnfq7/SlKPRHA6GEhL1YwNFitxjyjtvis9D+hESggRL8yti5p5H3NTEJAFyMPfK+84C5duqgi/MCDBS+ibmgOoeEEEnbswu2aJApado9gmDm+kxeFmDSlRgfnd0c8fE25wEQr6i0N9AxMhbM1JXrowLVNBYkZZtChZPWXtKgtqZRzPMw7ztsvFP2RNVXw4TZBKaOcU4QsXgYsOymBtQO9JuTvm3XEvhLsIB5JYgLEM1INaFa7hMYZ03Ovjpa1p0xTtkLK/8Lb1BYBD5KzNsltoNuMxnNoUG+KxznhbryPNUiu/VgUQmHeWsFvuYwjAPQrnYbNvIFznFWtVF7dvGGH9uRy1LeRbTbah6oC6BXuueff/79IVPkk3mC3boKuU9jRL31Rv6wHnlmMj2oQjS+EdXRko4ah1ktBwRJfpdre71xoBgKvcU33dUs/csHAHQa7GudaEOdXIjvDU1pMRTQHg1grE3dWDklBdxIwaMhOWXHZg525boIXeryMLyNNpvb1DL/Tnz7wTTQs+mu8jrOTP08dQQzGCA607GftTm3ZE2XdFdS7u7Z1jCK7Sis/le1zzigOtuLWCcz+43AYnpgnjoTYTKJvDi3SuGWvJOG0Z59OEeSlYpg3vsWAqU9z/i/mMOamuypKKkUj12bluiGvM3JcZxzJrpWHu8zVS6tnKMQijmZdkywkv8lm5SQw08+BMVHFNWlE5JOJtbs7uPW0MJlUFFigA8ZeTSI1KLS4KLafAohswGI1aSCSkB31WLkXwKNvDPQq+6dva6facrgUDEGCgzR1wBD/M1n8uem5JDUjda0ui6xlNTb37tt6TceEkrCo8kle/tHV3IEm6seVAgqB8EGEzqN2bIdC1bDhfdUE1ghlyw3j5EHmShhlnXPA7Q2TMY2OXiGzn+fC9unn1PicYAcQ6S9qIzsx68HTQgKnDBjc2R6vhkhrCFpFVMVjIkZ5q14KzgM2X/1g6HEogusxSIb3hR2WL3dh2ZB0xyeGrltHh8ToyfRRpiDRgkDyOzQ3ju5vI4Vreu/XF3aVsVV0baWawncc9H8EvILJsA+kkMKEOPDykEum0vhgMD2N89p/WxvlBADx8Y6nOIR42NvM68RDCAmEgLveJ6N4XcnK79EuKkAk5pdgg/f/Pll54gMpjN/Jy5z11US3pfdeclOlAJsIooi7xxqoxM8pL725NaPczGHwW2lCyYbFaM54FMVHGA2sFWS+ktiWXyFZr/rYcUKULlwFmpVulXAcBG6XYwMYwhAtqbRYO0k2vr2AP6JtieD6GAVJLeZDzhqAFOOnZH4DKhXtNGm+hdEo9zFD8uVl/PE3ZPXiuZ+EhAwBY68A1Sd0DtEC5Dgfewss1ys0r8VhTTlfWlOuZDrinJcjFY2Pzjh1oDY9UIwvL2XPcoB6szbw3Hr7S548Id9bKKJx0mZJRulzH9HIOVeo8EZe1L8Im0w7jluy/57/72Pr82lpSA9CtS2HAvYXGyXEwG2tG9KV7OUCy07QBzMvhf5e+3jtJMqqHA2a9d6MvWqw3PUvOl4RLxWgAPa3ffzdjh6wPUrtkwhj+lsHVMN5DLCyjJx7Dvjhc3w0ouVyMPtTi3B1MhYFP0sGJ90eGulmXfXFZCw9RfQ/tewIfP/dzP4d/+S//JX7jN34DV1dX+NN/+k/j7/29v4c/8Af+QBxzOp3wt/7W38I/+2f/DOfzGT/+4z+Of/SP/hG+8IUvfG8de9A78Y1w98DGzyopOXCmkNf2WBWSdFVS28xqYU0JBfpGnBpkgpUu7tcyDLCrB0Ms4TUBqRwv7DhxbgDQs2Kcc7EZjDTQEDsAC8SfwnifpN6KkVApIS/viHr8nWIScTES6eJwF+B1AD2gQPot9+u5FgYCVPk46XdrYwgJzpuVPjeXreuAkCF3qQxk5Qk06SqVAMztqwufWyFUVTgMBLTDBTel9VtsBJArssYLaGRhhgJNf17cX6JwDxqDXMhQezGODHUClq3haJM9G3LBMrMYMqJvkhXMuLfNBcrerlexwALAufXN75rP+DjdRXgF6KTRCjKBKQ3LeH2PzUiGnvGhBFEVYmqJw8LnxmBSzYMqjIfiXoUOGqsQTuuEnBryvGJJBUsuKt09iIuV5sQ//e51XjGR1pCpQrgvSxQqm1PFTVojO8It5buy4A4LvnJ+s9MHARD34EJlt9sh/jaKXu2BUz9HcA9A8R2GhBhbJSvJXqbOxTAX/ghu1ooo034yjtKSlFh9Pa+7c/vm3AyIjBVXXVvlVLs0++v8gN81vcWBPfRUVCnU7yG0QXIPQ9n5POTmIR8IdqBJ9TEM4Jm0+l1dcG+EUweiM1c0I2QG4bMmbJxRtoSyJWyzlkPwQmzfKtdILMALYK4lvA89ZVxwrjnSrgFYWCRhljp4QVrooriKaqYaYacFBS9Ml8Xv2eXhAeC+zrjblt38XWvC7b3OlZxNe2jQaQHM8NmSrkMDiVsqgVYGnwn5XtfAekBkPfYDsVtfRwoAgCGLhTR0vpgVYk4YBzbhMXWPvVycP87Zifucx70J2JWdsGuMnOjY64ZEiB03jgR17sYmVQKdSTmVQxZM3+z8d9tTin6Hq3pNnLSvgGOQWB/G57tt3wM9BPiVX/kV/ORP/iR+7dd+Df/u3/07bNuGv/AX/gLu7+/jmL/5N/8m/s2/+Tf4F//iX+BXfuVX8JWvfAV/6S/9pe+tVwBG+LYboCC5DB4GAxxBnnQrd+B5+IlcRvdSQp3cSn7q59OQ5LAJjrni3jdKLchEu4f96OaGcz31EKk7afw7I98k0Gf4xPpLE0DXrfXLyU8Dcr8AetFNsySqpbs5oNhZ2mMa8tAeWd6jF2McPwzXDg8S+vNm76f0l9J+HHQK93tRZcL9POl+yGExAB79TsOiEeGzcTz8eXiM2AGJaMy+OLnT3PFVdAPU7JJi9VIKbmjDKzrjJZ/whh/wJh3xJt1bXZRTz0Dxsvd0wX0YVqJLXoiPvT83759bwP7sXLp8Me0NVRLVz3bESpjrvuVQzAQQ6ZULdxe9b5xKRFVegJMT/cc1IkYp+F3fh419bCP3hC8eTJSAd87EcF4HLK7bcdkcZF9yTfq5e4n5aQhJeCXXQ97UcxNhIPVyBKnYuSlgbEiR9XLflp3cvoejHHCO75h7jKqM3BQHVim4H32OtODHOMHUQYYAFnpWES6fK6WxZo3UFOqoq3s6WrJ0YNqNC4AoLVDa3lvj/X4EIAduVFfw7Qq09eJ4f0ZaAK6Xchj1O8RAQRSRq/ZTeKcyTRdr5eViMIqE9TXILzJ8FzC+xrAn7Tp8cWrRc/tPTN9GeLw5jB1C56N82iY/7gdj3y84KAEaLvbBR5eVi2OHf3fX/LQ98gPte/J8/NIv/dLu93/6T/8pfvAHfxC//uu/jj/7Z/8s3r17h3/yT/4JfvEXfxF//s//eQDAL/zCL+AP/aE/hF/7tV/Dn/pTf+q7vlbLvB8c3zj8V39wIXuLKMneS9cP37EBEjCI6xB6QYQLPtjcmi4MsKCymuEyZL+ECp5NRMqWqpoERA2VBY0YOOks6IJXfg1FOcSkaZ3SwUXwD7Kh0abX222WLrHO6AXVAC2OZOTLHalqGsAaiYUX9uXjyUEZ9KU/m2jPtiVdpKhvaAAwLUXJpjUhZVVDBRAVO30xD/eigQzJ6NZDeDwuXv4hi+fS7ahxS3eNIDRNZJb9OQJIdL2UKKhEOgkoxsuVB8c3UuJRkQMP7qDIThGhFr9v19B4mU5a4Mx4GyeaMFHFDK8IK3hFmmXyhh8iY+IkE76aXuPUJnySXvQQjRBWyjjVCe/OV6HY6SRMTWcmnIsSOx0wsrmlHzYNA7026fI30xHXaY3KrYCGV1RzQrkDb7drMASvp1N4ORYuoSwKKCBItknvhK/qHJsnYJYuCa6gIOGY5kib9eZeiJm7O97vbSLd8DMpEXSjtEsF1rnHkT7spNjfPH8uBNkiTZkbriblJwX4gES4Yk76DF3V1bkwmm46kF5BwY2ZyLxEMivQ8Jot5s0a05GBvZaKE0+LKCnY+3FuGe/KNY5GCPZznu18L/MZbGmwnu20mox8NU9VE0LKDbIpHPJy8rullkTTdAuhJQ3vvZjOIQ5XZcNNWnFfZ5xKz3Zz8q5n53i/9TMJ4PYinfEinfCKHyJT6rZdRWjMOUSZa6yrQb7NNfpcq3JlmLWwXPWMF7+ZwuaNYKAC6aTvd5t0PaWGXhHdDZ9Kkd3iESHfT8Q9CxjWJPc4uPHpi4RntNia1TNGxmXJvLRglRyY9Fqqx4FeDM44gsIAr31voKb3pARQ61OyPcAydiJ7snVPdximZlgFDvM1tfkaCT3A7msEHm7wxmffIwD5/4nz8e7dOwDARx99BAD49V//dWzbhh/7sR+LY/7gH/yD+L2/9/fiV3/1V58EH+fzGedzFwB6//49AL/poZn1u0Ok6GgzwMiIzEaL1b9XAWGGtAaBgZQ45umfCLt4vQ8gFEw7cjXgY/EBMRU+4bZ/JmQX8nOPaVI0Xpf6gw0NkR5aicnu3xuzOz7UIoYHtep9M2V6En1dfvTYynBil6btudeD6CJ+icfzkhggZ2ULlB9zeeC4GsrTf39UV+FD3x+zaXwYRhAzjtvwOQ0Lx5MtXsB+XrYNqiuc7r/ryqWAKz9qBgijRbl5T6NkamCx4mwW21fL2Eu/26JAYkS7rtNwyQHZvN6QuW1qA9asG9MhbTi3rOqkhNDwmKSDAd3cNTSTuYZ+xyUZcyTMpmHT9818LDYW+h7VQxuMJv7vh9VNw7NhVvgmCYuUIWyh/emWden8msEL55LzcnGdBgqNjCYcuhmZurjaWFjOr1dB8ewgGSfpz8C9GXf1gK2lHQgDOvhwsbXx+fq8iv4JIw1AbdJ4q8nj92wc9YylyHLZrPClCDoPwprzf8bm83dXLuCJsbr8f82C6R6PamuEVkXePyO9zmNPVGT8gEJgbBQjFFswJd4BCkXTfVbL8O77d520/qFGw0+cbzRmpBtvfrytF/5YhPpeJOa5CCDjfd6tV2RAqHtuwiOyswrRM/d8PwCiblnwWAYvCcX9y36t+7QhEMS+AyOo9gSQ4b69H98v8NFaw9/4G38Df+bP/Bn8kT/yRwAAX/3qVzHPM968ebM79gtf+AK++tWvPnmen/u5n8PP/uzPPvpcmPqNhSseWvjM67qkvol7dofYhGGLazWfQOatoKIei21QjhtBRsSx0GN7XtmwgaN0vW/g3mhjZfu616UmCAnqTJq/7Rvg+LAqdS4GDI1PEkg1rl8B8ckkGn9zJOsolqodbwu8vzjuNpPJ5osBmny0e5psXC9E3QAMIaq+wXnFWmeTNyG01TaQSU/OxgXZajIBMfUuOaMgsSBPBYWSVp0cgANtT7wZg3UBszw8X13G/vL4QlK/IPyY/hLHMy5A8EagfJldfy65HgRbeCi8SQ4g60vlv7yeH/B6OuEmK6h2VdAKUqt3U+vXS6pH+IIEn5/usJgaqpISnXfQQrDqLBn/4/TaNnKN77+YzurNKBMe1hm1USjS+uJ/Wqcg50VdHsuCuV9mvJ+u8PFyj5fTCa/zg4Z8eA0gAgAf5fvoz6WctwOCBa5VskWWR0JDnfQ+XcXzvi04twnf3F5gTVqQbW0Zt+uhkxNbB0wO5nRK6L/HMiNTw3lSXsJSuyfC66v4JueVgHWT1+yazTZlJ+KiMYTVW+Rk19rUAr/J550Y27h5OpHVPUWqw6FWvqel+jN2q95DI4vpZ2RuYNvgPN00C+HBfxeXpvfsE8HJpOJ/YL4F0D0+xzaDm8QY3q4LTlvGw3nWMItlL3CqYAPWrZmuh8kQLKngkAqu8xrAx5VWtY/K5RhTlRlqeJxqthRe9bbdr3PPdoPgfMiRCQUoj6SLsh0MwOr43G8zjtuEt3dXUUEbsM1WegidaAi1jF4I34zNyyoCIPvvouvL5QbPojyLoYyD70lKxgTaPHhrm17f+XWxZlhri/QwMKFrRrkXxUBHe+iyBf3L6CTZZsCDVUWbBEhnCm+Ky0JIlp0TxpYt/ZsBFgUX2v8xCkkChO4j6z47eqZdoDIM99rLWnwvAOR/M/j4yZ/8SfyX//Jf8B//43/833oKAMDP/MzP4Mtf/nL8/v79e3zpS1+KLI3Y5EcOwBPxNbFN+HIDjaJwQHe7Wzw/QjPjw6buYYhzD0xmcnQqg9dimCcKCDQ/nHhA4YZCJXnVWPTvjlkTA6IMIrj/0XZWrS2Djqj9eNe9kOE9ugDOUQAPOqG57gsOfcgaaEJRITJS2cyC9jBXq9qvBgZR0w0urmubxjhWPt6E7tV6yiKIjBcE0BydOE40jqHGMC6XzzIGejjn+O9FE3sBA+hIP+cYnunjq9oTrnDqi2voOBCbC7kPdJQ+b4x3dIWFJ2xJs0OOrReN84wZJ7L20ErTUB91L8uoyTJybfqP3oc/x2paCvd1jn6drB+9DsnIdEuR+jturgBUjMu8NhWMJFpMzFN8XZjMwcu57fU+3FXv/CIBAmiFZY1eaIyTRJXUHddjN8ZazGwb+Ai77C371/kQPllqY2ymP/JQp6hbMyqRAuq1cNEtb6PsuoeJJuPGNCFMrqliejCePu3zRmunTFjNv90M0Ix1ap5qLrv/UGfj5+R4/p7ld5kh4nPGx6NYoTbtu3uZOH4Pef+iuixp4AaNG2cdPBaJYce5QbL37FRwJ19L1/qorYuHARhru4UBBDQQdd7KznsN9MxA12xyD8BogPq/IxiJfQHYaXcMXoXwfIan2g7xMLevzSwqcmlE9qh2vnsI/dqR4ts66X1n8A7DHbIM/vmoQeK3MdxrhJUhnUs4tsvPLv/fX69hjB995zu0/03g46d+6qfwb//tv8V/+A//AT/0Qz8Un3/xi1/Euq54+/btzvvxta99DV/84hefPNeyLFiW5dHnLn/tP8JQ1w/BCvvYw/fQgyG9ZjEzwDZXz6KYgOBa0Hg+dx/0zZvP1Df90VXm1vBmpKWC4BcEihRHkSZQA/2uEk+dAIUuWmXpWFQAYt28tW82aR2BDs09L2PtAMkAMnruOQ/vzqjL7+iUFATxkSAT0G6glsDUrMs2bqKENGaNr7rVJAbConCee0kMlWMik05Hd7mip96Fe1SHqqNqGcfQ/uwF5Aw48ja8WARsL9ArDPv8QD9PeFPM7Sv8+A3ZreMOZIy0GtwOB5y2yFCxCpLumSFdGF16erRkiyR8e7s2SW59oAsVTKnimhnf2m5wbhnf2m4AYG/lU898UG2QjCWV4e+Cc9Osk3FzLTWBSFCNUKjjrgq0AHabz9Y0O6Y2xns+4NvrldZfCZ6DbhovknpzdHNMQwpwz065ShuWVPAyn3DgDa/TQxAwAbXKm/FIjnXGJ9vNTuysiW5qqk2ic22tCS3bpkQ9e8VFvZx7cs1rpPhug6drVJodgZ+DmnFzmy17ojRRD8g64TbpGnUyFVEPRYzKr6Ul3JUFDMGr+SFq5kxc8ZrVk/QyPUSYbWzOe1glq6YLCMe6WHVaBT8FA4gxrZBmoMo9Hq658rXzK6wt4W7TujAONlQHg4fQBEG490WEcD5nEAHf5ivk1HDMc4SAJm64ntaoIOvgYM4FEz8GQ2eruaLXb3g5n3GdVedGs7gulF5FORzHNuO+zDjVnnGlVbUp+lmrVdZeGZJJhSKNYPoozGpr7aXRGuKPw0YPV4M2Hp1m0kHXxmGT1474mtDT9Ns8cDsSlFeWVTqdZw0Mtmz93Lhbg5etkHJUxg1eBtCRbOldbG2y67usOsP4JMO+6esoF/1Xhd9k56XRfW+w7nx9HgzuMStTfI/O9Jgu8SntewIfIoKf/umfxr/6V/8K//7f/3v8/t//+3d//+Ef/mFM04Rf/uVfxk/8xE8AAP7rf/2v+G//7b/hR3/0R7+XS4E3Mbc2gmAZlfcAwEMLohMo1pMhNi8s6l6zw/ss9APQpbMDudLeAzBY0Gh7ZB/HCAWydCt4tLwhgFR+mtQaL8ZgWX+gjc6ZuD+zwsOi341LP99ILjVoBqoCFjKlUOlo2/vl5MyLxbk50LAiRIHGHcc1aBpoI4iwuXVHy2W4SUf/DqIGIBJhFnTgQWaZ7ICL94GkE0Htb0L76z0yFi8tn3GsfUzc4rh8Nv7cgPA80BAfT2ho6F6KqBKazjvNC0CtXxcQA3whpvhXMxwQnzl/AnDPRs88UtIkwhPiPAiP8XfCr9j38ah5zP4o3RPCJLjnxcBQi+yX8e+ukFqFQtWyCu+8Ei6+dm4ZDyZWVRrjVKcIgXiWjYf6Rr6Dk22bMM4lB8dh9MyM6bXOf8jcgAacjQcxeoQ8G6gNG2i2Ks6JJQAQQ9A8C0gInrTr3JFMNQTRrtKmBF6rDOthqLgPaEaHpthygA6XFz9LxrHNeLddDc9lv0v5WLyvB7guRpMuo+/PxYm0ZRDx841Y39PHFspl9s/YXF1257EavG2ALa9D2Axwb133Tp2ke4o83fzymt7/nJpm1ISIGJsXmiCVUQfl6Qi1XOzsl5zB6Kh7A6r2K46iYS245HcEwOnDBvT1ebecCyKM7YaMP4OoYI7RgKUwaMXP6SezfVG8f8Mdkn23+TovBGpDJiMNoxH7oO4FsYcB4RlVb7wpTo19IEQEwj0tQQX4Ltv3BD5+8id/Er/4i7+If/2v/zVevnwZPI7Xr1/j6uoKr1+/xl//638dX/7yl/HRRx/h1atX+Omf/mn86I/+6PeU6QIA6VzBBfZDaBbGABCD4ixoR2qPUBcDbfJgGLqLXAiRHeEx+8G13wvD2aJtL6xP3AAK2WqrVFg8D6o1gY4QPZYnl+41bzKgU2+jS8/6pJ/vf1cXomgccIjPkcUdqXQwUQ8CcK+e2ya9r5Swe0Eii0agCqS1u+Zdjl4KQwr1ir0OCsMlqGCsZlaUz62DmKlGFgwBGvOstGOQg4DGHp4iYLNn4Atdkt3MJSCkhp2PEYsFCyTbi+Fqfg290N4AcNAvESvIKCgmBjYiVOQVlv3SqacyXpJMM1d8lO9xzWd8lO9MIKqEyNQ2O1dAY+FebOzr66uezSCMB/FsjhbiXp4VMYIPvaaSndeiG62CQBUlg00dkZ5mOaZjalgj4bypkNS5ZAjUI5NYLVgApptRMaeCmTRdt5kXYG0Zt8MYjLLlY9jEuRcuqw4AS1aPgadvzvzYU3BuGcd1wmWr5rZ3AufoNTrkDQ9t3nFhtsrhGUrcx2LmgiUlbNmE1czLon3vRQN9s2cSvJmPuEobXuUTXqQzPpfvccNnXA9VdTfJWCXhaJouLiZ2rPMuTLdJwifrNb56/wpLKriZzvH3qgS4mBtfPb0KqX0AoUMC6IZ/yCYxb14vsfAwkXnCROcvAQb47H0YNmt/9u7Rc90QB26eURXCZja/xnOMoSIn317+zQG3A5wpVeWgTAWlsvJWKqMWd0lANYN8F3arPApJinoYGnq4G+hGjodPiyuRQjlybsiElW//euaHeZ7d2BHbD6QNtq4vA42AgqhZFnIPDAgk6nURDV4YUi/KeF1qxvGQ3n/xe4CBlg3Kf3FgUEwDKw1ZNMNe4uFjsXtQ9EF9z2QgeOeCUEcdq/s675BGnt13aN8T+PjH//gfAwD+3J/7c7vPf+EXfgF/9a/+VQDA3//7fx/MjJ/4iZ/YiYx9r02SunBCDnbwMkS2hyAetAyDCSAGd4dOh4HbHet/31nc9BjFDQQm1QXp1jC1zvPYn5vUtHQ07iIywMA3sWMDSGGw2se+2Xd5iAFGX72a4cW9mFuEDHnHy+hj5BtvMdJQs411CPW0yppJHC+MgLIdO+Sn7zJ3/H3lZsPUKwsA3UsQ/fSxsvPH556Ka+MY4S1CuBc9lKa3Sibu1jOP3HMR8waDgeTjJbS3LsgtEelhmot+OmkrPrJxcPn5UTAJGBdXdzcvAUBGq11TNc+YpKJNar2/KypV3qq6/3UDHKp8wlMZ+wbyIcXTkTh8WX3Yz+MFwDhLWPX+t57u2jBn1bi4yavJquvqs+e6qD6EFvvqhck2UVVVB2oPZYoNDMCTq1MbTDcm9Up0xdduOXtfISp37gqgQCerukU9pYZKQKm8OyZqurjXoOTI7Dmkohk/w/gxBC+n0y4F1wsK9vo33cPhkvm+2d7VRdVwPcsGCi6XVAJQ6ryimFk9s0jBknuM3DN2KhNOQlrIcQh/Oi9itxyYJSui52fz/EwWhvL5/WBS7F5ywT1HQvKozsrl/Ftbxqk23JcFZ8448aTqr1FJWUHixlbTxYrgjTo1tV6c19e58MDS8GKir71MPSTra59QGCHBxbgwHHYAwjZ6AN0TP3TFM00aRMMeg7HiG5VUQNa0M4jGDJhY931NM69DGIVD/4H+ua7bAkx2n9zLgFyGdYQQNAa/RxJEnSzfp+Jvwzr5SK+qYVfB97tt33PY5Tu1w+GAn//5n8fP//zPfy+nftRaZsvFhuYmB+FzGAgg3FONdeB32hjjpgIEHyAQ20gUatT1QmR/HUmODmGDS31C+djYOR6RknymNCjbkpsRj6Bhi8axMbokbwCnHfEJA1I3QOGbvWBAKfodAXRy+aQNZIzuGXB3fENwF6SSMsI9xUqgMeIhC4U9JgpE3JIG74XYS+bAoyvCXkoIS2QhxUfVXjbqVYzbJB1Z1x5iS+Z+hNe0EtcxMW8SWUaKK/7Z+Z2ZLp4BNYCIPgH7C+qeKXcv+niyqf+B9O9FAFfA1IJYnXDqREEAsSGd27QrLDcWcHtluhk3fMYqTj6drVpoCm+HC3Tt3dq66Fx6X3rWkk6a0a2+s04hmFNVIa6k5Ei3pB2UAOpZuUmrWfoPoX3Rh1BDH5c8lisrS/9QZ2zGxRhTMlezzpsQJqsx8qHmREdPtXX9DN/4XXPjOp13bn3PEsqmRwHswQfQQwuJG87bhLUkXE0KYlyM7SafI+V41PvQ+21KEKaEI2Yc69Kf4cDNcQLn+7Lo5lz2EvBe62YUFEs2oVXgrYVq68t8DoDkqrKuRDumqeoJO/EYACTVSNdsrFlpsym+6phZZtTWeRgKPMyDgkGszC8xVM/1bKwmFLotEzW8mY6YphrAw39K03m+1RS8nCqEVlPX5oh12I0gW3PZ/t/vOcn+99Bq0o81UYXA8kQK7lOGKAEyXS4asLVa16DqwMM5g5ahAlGl1eCYeH98v6Bu8Iz7ULzOBA3zjvuCgw/T+Ohh9riFGCLy/dG0QeIaTQ06zewkO1/fB3ydrBcRBqp9L3rC1vlg+8zWdlEiJzpZ5mIQAxU6uvM/Xs4HurC5HXDEPm1ZKSOYuBjBnTcBHaR6qMQf4A6JWrjFN6+YgGNfBxAVbrURpV4ym0ewIR0g0HBO74ftL0GIDfDmqH2w5oXVwwQgQjfhSiyshLQ0YC2K2rkXqH/oLIkJ/+iP5+BX5764VUTQFy8RIDJ4fnQgJEu4IMfnS6J9poShno30ufKEARPPym89xqKPKWR3Sz0G6+fy+cYGkqxDft4mhGPReiY8WA8VWkq9QjfYu3rAu2LFyahnakQpeD4Hl8EBzF4+nLDVCaeqImPbbjPT6xar0FqNYOgp0CISOgK1MogQG34/h4ZnnFx5nRUw9I2IQm49cw3CJIDhXtrOq+PaH16p1wWl3m7XKC1hSjX0KEQINe05HOO9AQpmfHO8rPjqGhxVeMc18T562KUM3iO39ONcojwPTyWdkvJKVD68Br/Fr9uMi+OS8f7c3RPi8u4AIhvKnz2Andy8k3kdOGh/lNNxrAsadx7NgTd8NB9RWoo+PdQpgMxW1bskRKgCBQNOvhyMglAnFgUg5y3Hhg8Aa8nh1Rg9KK4tM/4e2XCw940V3J1LRqYWAnUvkqYv+7hVqAfori7xLMXOa683mBuaop1H+iy9OrVd2KfL5Vrg3/NN2V7yZjmjj5wfT+n8hEE4/s2BnPRwdP84/j8KVtrXI1141DGhYY0XWH2uYU0Kb8TwM6x/u+b7W5K+rzre8bATEKCOAEvJNUMuD9e3pcIBB59U5oILIL8TCsu1TBZyGXaDAeHB/he8f0B4PA86ogRCuU3RKWKz9b+N3w8Pb7uYjIEye9/8AcZ1HAnGG9MBQJxD9hOd2njR4TbinMN34/6sAN0lQpa+Qe8Y2s1gw8UY7lRRPc7ZoPHCTCoIhnhXDaz1hyEkuxQ42GbMLOYyZrQGtJp2ufp+bNS7sWcSL7VZNRFCCVIZom4Lm1syOhiKpbsumrDS+PI6Ubi7EcmF5MabBQIAjVaRNOgb1LB7Zscyg0kJpkAn453bhA0ZExe8K1d4W65xrqo54V4Bz2L5eL7DQqoc2mtqqIWNBhRKBnRmHLcZp5JxyCXi4wzNYBkl8HkAhS6pDRithnTDd/c+k2CWCs5bkGX1nhSEFNtol6GgmaYQE1JSmu3BZORfpyMSNVxz18aoINzWKxyb1u54qFP3QJQESbrpjenDl40huMpbhAXGzzmIWt2zMAp4OV/B00oBBxcuDNcMvClxk6jzHTI7sGoh2d6Jwhpm+mS7CY7LwiU0X/R3lcpXFdSKydRKfVxc/+W2HIwHs2itGwvD+Ma8kM6VhQo+P931DCBJeLdd4cHAaREehP8o1ECbLQzOVdoRTEX5ITo+Ooe2kiJjhuBePjVC6sCb2QMPJzkbR6kmXE0Kap0bk0hBnfd/rFED4FEZB04NqIzqRdekW6fUSHlksWjau+rrIGALo59M+r9NvapU0Dl643l2666vH6JrQPzdFg5f832dv9i7AoCEQTnwGIHBWwKg2Rpvyxy5AWQepyDi9xegr6c+NP7ZDpiIjlUDZKVYs8P7T/YsLesPDpJ8fbaszbQCfNZ/6+8E8EFVQwGtEnjtAwgMg5n6YEbJeHriB4jNafcAhr+NCqm+GanglE7kHe/EN8tL95xfB9jxSlykDBWAk7ucHeyH0fgdf5F2v3Zw5S5Pk/SGDJiFOooW4JGinm/MI8YRRnchDpsoibslh80LutBIJcg57Qi7ERKxeCNzCwvJyap5ql0rpJmuYYORt0jHoFin6PEYC+n5/T0fI1syo2u9DOMCC8GNIZudl8bvW4YxT9hZGFSG+K1do02y84r5vV7nFdd5DfCx2uebJLxIJ3yU7vE6PRjvIUeGw6hv4DH7r22vgjcxEk+9hoemha6YUg35dNfGqKav4GEYv03mhpSAWvx5EoCkno6UQQBmrlgBFCPCHdIW3AdPM60gbM5BsU3WvSBeTn6iitfpGMfAgICWju9hCL/nOVUc5i02S88yccvam276HSi5oNdYqMzDHGnII1R5cBVOezGpd+lUcmxwKpyVI5SRqGFONbwjY3aPpx8D2KXcemryzC2k9Z3X4EDjUhW1T3BWUMGCwlqccDUA4WMQoQnuYSb36jzUCUUS7ovK4Wcv/kiCanPClXCJBOTeW9HsNAiieOaUK3KqOEzm7RpAgHsiYN41AAPAQZc5h65H25aQEqGmquTilnAltAvTeRsFzc7xbDqgSeYRa02LhArXLi52TiZC6IvmaESiL5Ix3uiGpLdxbXDQMPBIwsgUgJjQIqYNC10QukQDAohQblHUtAGK+ovsDNCdseNUAkcBHt7wkLdrljgocbztGUADANEuko3HoBRuCQbNi8+NAMnHB+gJAd43XyvbxTg/bSc82T674KNJEFmoGgqrugEQm3pbEDMtXclR2piDPIIAD3VQ/x5wATx88G2TjxALIZjAly64p9K3RoIsBsE0Xnm/yV1a+YZ0+46K/YQc+uSnp+FSwHA+DN8dwgPxd/8yyQ7IxYvVNAXskcx61dQ2FBrqBlBIpjRWF27UhfFuEZCzWubbllHR+jgXu69kC2CxF8W9Uz6xHVzQwCy367Sxlov0W5QEeBqYh5RG3tD+5obn4i/vwPOIrCQa3ZfauWxW+sHqgLiYVIG6vbeWkJLgZXqIYmP6WNmq2ab497YdcG4T3pcDiqTwkJQLkaxMFZx0077f5qjj4rH4sECHW0yk7w95FlJjVDS0llByRU4qLT4DOEsnjs7GJdAicghS5FMFwBrpZj1xDQvfWwWbRHyOTdO9HJkbptx5JZGN8sQ7pnOqS9i7qqpfw8W2AN3QtJR9DQnyg/FZmA4Qs+KjAKBN+khTtVDQueQAKaOA2PhMDmnDx8s9rtKG1/mh805YCwS6lPhliq2eS8MoaDDyaAvg4cXWnFCaINiAXWbPQ51xNsCiQm8WUoEDBkuB936T9CJtJjnAcwWnhtnBRy67+6sGODQ8pt/vzwOmoIudB8QVVZuB49IUbO+E64bGJCGpfpk14+DDwTOzoDFBmNBWfszXA3q9L2+DgSdsx4xedmAAFPu518O8usFTouHYDj5g3hYvhEnJQ9ACTFDBQeL9pu1G0G4LsFRXoIdofN2m8Tu2dlbstJ3ifpsaTgQKD0vsQ27QDYab8gr7Pfu1HHTsSKhPv56f2j6z4COdG9IK83AQWhbI1Ad/FycD9bRHGn6wR6l2MADsOB4RdvGUWxtY9mySRppGe2hqRbuXQKApXCPTd3x4QA+3XICFnSvMEe4TC+wQMYoXZgQ/ToSVhM7k3l3frnm52VpIKyI9DsD8u/FDqrHSutfAj3GiUdQycG9U0hdNc/MrEgu20kljbbRi/YVpw7VpABIkUdJ51CqJF731z3bhM8IeNHloiQaQ9sQLP44rKoFtfLnoHIQYDyX38dI03G5NXqUNL9IZ17wGGTRzs8/OATwOvGG2yfOSHwD0ui+37QonUULquU349nat4KSoy31rCRkNnARNWtRzif6TgAloMAVb0YKARLp4iyBE4NAw8HN6xVwAkWILGNjhaoRO3QBd3OsqbWGRjxobW034mrzaVS4F1Av0vhx23pyuq9E3pMQNJL1EfLtY6CJTps6xKXs7VvWquOdhVBLtJFcOjgmRpkl7MTvNIKngSXBnoY+HbcL9OmmIhhuupy28I5kqXi8nzFzwZnpQTRcPrZhqqYNL1/JoINzWg4KLgZwcqrfCOKQNK2U8FA3P+YYddWyo4Tqp8NcDTZiI8PFyH/PkSBPu1i7kWEtCfchd3ycmDXa/z7lgTjUIr6WpJ+bBhMO88m2tPdziJ6pWhNJJ5ylXpNSwTAVX0xZcoeiTefKquHhdihCXp4yftgy04XlxU++p6X1I5S4MNmQmjuHxmB62VkRtKRd+ZIA2LXvRZtuUXXhxEFQcDcDwCozAwTwNLTdgauDcQsZebA4Ti3qcPWtwaCEuaSAn0oHd20DdkPLjJIj3wyMNo6sbupGYMQII84qEN970SHZrpidVNCvx4X01gU/h30aRse9n49q616MATNQ3pNGbsLP2h9+9DVa8+JN56jjqJwv3kz244CHYD2VbHBtBquwqn8aEHAB9qOo5WoXlThsACU8MLgBI338ft+EwByjOTH4E8Hl4U+w2A3z5DBgNkNhUDey4S/NiccLwUoQEvXkMyFIgE4uFBIyl/sStXH7ooZUdaBwtl76uDAPePw9L4uIZ97DZ8MfBcojffU1uUDVVm4dMlhHVVE1xHIcxi8fLy/tG3KW1S5AEE7UIHczD4B+sANpMNSqhHknLrHMTlGQZAOZNYQgKeFfJVqBAQb0CZnk2q+dBvZhYZL34UHzAZxqZKLYx7CXDNXb/Oj1ESEHVRVNY460SHjDtQE0TwkObd9of3i5ThD/E+dj10bwcR+paFw5qgD1ZN0TZoJ4b9xJl4z54OMVF01gaEk8gEpRq1njTqs1zqmGJMwluBlGxFOfpFX5dudRl6SsYt+UQ6bU+fwArFgcNgV2WqfdUa783hmDy1N+QcGc8YMLKe0VbEVIulwte2aZIaZ+NlswTFZlO3LTPFs6r5kVxDtcI9pvo+ZOlrjIrVyRzr0zs4m/10mtm9+aZPBF+M9uw6w7ZEmHAQxrF5uite3r382XUqAieCCQ8BztjbVwjRiPJzvGU88YBSHizCXEf/SA7BwY1bP+Tv6PmrQ/P8uDpdcwQBq2F9i8ByFieZFR4jX1u2E89ZBOeDgcsSWvciE8XDwsBnVM4hry/i/aZBR/lkNFmWLE1oM5amEeGiUSVgILOAAYeWfxuJXvWhMfuadyAAbVoyXQ6SgcdAmXxNrueAF3Zs1BnVwO7zZmtlHPzOe0hm0mfeCBJU1jlC7IraJgc/pFfZwQusr9PuJNOOuodZ8RlATmBeRbO+5di946cGNgYNTcLC6Hv8NTRuAswgRltsxh1gcWcgZwq1pJ3nA9kfZvqcO14jgOwHIGVe7icg5FWCgA4zo84ByG8F/q34VjjwNB4zmHsuPTfg+19AWxcgj0PL/alxgeA4EF8q7wIMTGXyvY02wOvITwGAG/SETesZdKPbca3txstby/GB2g9LTVxw5JLZGcU21QB82wkjf+Xsvc8aaaHplkmVuv/Km84pA0vZ+VQ+CZ0lTZMXPEmH7GwEmJdOt03z2tWMayP8n238q0WjJJm1ZLeBh4L0w3ebwe4SJuHW7yNYY7+Ge+EyYBeJde9TQs/qMcpnR9Jq99tC+7WBWfL9MnJvB1JtUsmrgGOXH0V8waxc2du+NxyxJwqXk8PJp1/NhCgBEonj55bjuyWCP9Y5tDrpF6vs3FTRg/RbT1o2EUYp6qA5a4syicaHqOCWeBNPva6MJbGvBpPJUIXJJ3QaHPALRhBr1nzsE0qu79NEX4SISy5xLu9SUbZulKha/1JpLh2sOCy7iK9ErHPi7E5kHo5n7C0HPVjjucJtTKKZ2YJdeBRKKTKZepyCiGa1XQj33mHva+emeJGagKayJDab0BgIKk218gYN+zR4GRo6HkjhYa5acZg6B5ZX91b6yJpOgC9eKkAJGzebTHvQgc9bhh1Th9MKgEdHCTfb54wTDPg+1F4c8QlK1SwzMNS3r82CzD1Pbd7hnW//m7bZxZ8uJtICOoevCB8xkP3AY1a9/Z9GMC4zEk2NKqHP0acuz7YOXTTkz453PUl9ChDRr9IcOtZr0cGEqyPARRIkapgcN0N1v1o2V+c/jKM82Tnxfs+fG/srPR/dwJhjC4ABigxykILu5DMYBG4PgCZC1HMIqpEo+K9nl+oO67InmvadXJ/vJOuyjgm9sLEwoJO9PIX2h+Z99GBg7WoxDiMxe73CzC4G7Phs/AuWXx9VPG8XFg1JTXj2BacJEd10sUqv95I0ri/cReSETuVz6Cqn5PsS9gDCK+Cez/Ggl0+lTTLBbsYfRQH9Gdi3/Pz+SbcuR7qvdFNtuxSgkFdHZShq+KCDcc2YxIFXkya5ZHQUNmzGw64M+Kq93/s31MeGed01Itw0xiy8EJu7pFp0DDjmIrsVXNjLOLeFWwxCBu61HozI8V/d0+Jj8soeOZhj7MVpWtMUZhuDEP5vwd5XMjNpfRHj9G5aWZQsrzIcS5MXMGi3jD37LSnVojx/SaJdW6c4ApcE8TvNTwzzd5dTZsP8cLLd5cknp/Yu+eKteP9Xd4Dm2dEs58KVmPFtsZaV2pcq8wrizpKlIuCHpLwTsAzU+KL3kd0MDbWLUkUVau7J1iP91BEPxftPSUY1prWw0BqIIwHDT/DWv24/gxive21WiTuN+7bjcbBeNwZkcMzcoN1lKHw7/p9jvfclZwHB4BfC5a+zxeh+e/QPrvgg9XNr5kY6MRMs0i92BiA2MjDggVsYG1T9U3GY1aQCMM4X2S0ImTSvObQkBgeJgRdb4NMfAqk5MsanQkCT7zPFgMUc7MhNUO+UK+BcxeAmMy7PO5x0o/gy64FwAriDQAB2JE1SRB1AZq79ZrJsLuAmo2xJARfRhaLTTrS9bLzPpGN0MmbLgY1CVAY25rRctttIM60ryVpKMf76q67cVG4AAAkCNEwrecj/R7dSwGoOq71i+xlkQRUFnAZ3JcCdT9TH8tmaXMBfieJsd69dBdriHMomIDb0uPrLoCFBny73OBFOuEmq8T6RJ3Id1uV4/HJdoOtPX4t91oZuhl50TJvpzqpFHpNkT5KNGS6kCAZ6S3UWCtBalIeQNFYumt+XE8Jh1Qwp4LPL/ehy+B92VrGJ+1FXP/YZtzVJTbWz033eMknvElHeDE1poYbS7l1ifGvWKbMbARdakqgTdzU22DNVWNdL8NJqhNX3KQzXqQzXudjhDe8PsrWMsAIEauX6YQEDZksueDF4YxSEx5Mqv24zCjMKDa2o6jaqWSsJWElHc+tqj7JsUyPCvFNXHHFK655xeenO7xIJ7zkk3k+yqNsl6MpoepnqoMCaBjCCaenoaT9mXOELs5tigJ0gMmrCw2hnIbVwHFKDbL0VOSwaDd1i8qkoY6cdIyuBl5LaeptcmVTIijvqKoXIjzBBIAIjQVoSTNtWHBMeu6HwwSG4K4spozbRdrcK/Tt9QqnOsX1mBsqUYRYvC4XDQKIut7t1/MAD6LGHgSglfrxSeI9Fw9LEtSDML7oVk07vCkAUAnJ150LTpqQrauV0FLSrLKrEryqFt4nMkFIifWQzmx9xgA8fFxHEDWMt4dWBo9EhH3GsRBo2B+drxdAwv+18DJZOCr0tnb11WwIvQ/fY/vMgo9wfY8b0OXvwM4iHS1Yj8OHGx19M+/AA3rCS1Q8dsM2711YZ4dyrBsDGPDvPTI4hokUfX/CKHk0DtJvy8HMbhwG5Hx5/OPzdfAFYJdBA0F3sRmfw7/ypMiOIWf3QAT50/rRRL0e7u59klPwhKfj8WXo4nfEc7Qh2gm8uidGFxPsxjg0YYbjxxd890zoYtyf6EP8LXgUn/4W+gaohNM1Pt8kAw04Y0Izl727pgFg2hWlwAezPwAMeg1xG9C4u/8dAFTrw2PL43c962Mz0h+3LsSl12VsA53ePTwPdVI3P2Vklxi3+3Xew0w17mUm4DSky44/4AY0RjNX/4eaH++A50AbKlmFXequbO8HMAA49Fo81azz2vp9uoVehjRcn8vV5thq6psTz6FT4t4QALhJEtV2r3kN4LGrait7WXgHWF6191xVEVX74fOCwaLeJgCRCeUer9m0dTI1ZKo7vRRNsZWY1BL/eXpsE3XJ9njmMsjgu+eE6NF7Io3ifRLSFNxIa8bjEgR+3cvrPDnf/R0cyKW79dUvCuw91I00BOt/9hB7eKYv1jvp77aqL6MbgI/WDnnsoTfjE1ZxV3aW7lP3NYAC/2jcT8Kt8eRXYyjQtNTEjnjv+4NEd2Pdjz5jf7x7b7wC+6O98mLv+W7bZxZ8pHNFfrCbZdJCaIvdYzYWrvEPYqBFrW+IoVaPjwFm3asSm34A4z+YBU00gBM75tJnNUwwnSDUs2M26tkxUAtaUneRjehbxqJ2Q560u8XEYorejzFn3X/fgV+Pb3rmzAhKLpnZfo3LUqYeuhjih5IttumuS78O0F+4Zql2xqcg6DmkEtqatNCeEXRH4aGUK5oV8ZJKnbS7Azl7RK0lsS20I0YGFagYnbshJR5PkGBHEbo2AZhbZ477i8PdQwK7B59XIImS0zpGBN4oxkyzfPTviRs+mo94mU+q5QECcMCBN/zg9B5v0hFfzG8t46WECmjNb1VjQjJWaKrtfVvw/zr/IE5twrtyFSGN+7rg1kSYuu6GaNl5A3lEPYVymR4r/5TKxr8RSKrIuSElrePhruGtprCgv3F6EZa9k0xzEBvJvBHKqXioVlSuHJCp4QfmW1ynFZ/L9wYQ1tDFGFVHD6ZU6vdSmYHSOR2b7DetkZsSYZhhYd8k4dQmvJ4e8Dod1dtAglpe4tQmq83Ss3tS2teKAVQw7qFMuFtnnLe+XDoIWYVAxOEByVeqgArW8MHn8tGyXs5oQrhvC5ocrH97jZdTm0KzozTGQ5vxfjvg7XoVMuMAAtgUSchwldSGlAQfWcXk67SiCuN9OeB9ucLaVC/jSIJsmRfbmq1wpL2XuYMnwHRiuOFctXJwbYy1JZxKxv15xsNx6Q7WJKBcgmjqabuy4+00bFtCmTjuwz1pzUz7CiUKK5eHQ+dlLZZVIwRKyhOLTTzJrjglkWU/DlY6bYOnvKl2lHvQ2wTUBs1uWVpfK73opW/Qxo8YvR6+TghDs+HcO2B7BRWTAzDNqIasUgSenem8QQvxaL2q/freJukcEHQgtQNUvgf6PmUZKVKpiz/6HkGI9cs/1/Vc9udqmvEpDpxsP9W6a/1Y3rTfXIH2O0JkbCDTUDWAP6QfRTiBHoPdaKMl3DoJcxdCsWvtvBHRCT1gFJyKzarBXHh9Ul9a4DsPhAx/GK4tJEM4xj4byEI+seMUw+ligro3I/o93IJvsAaC4qjL++QeAiHzjPS+D8d+CNmSFWWy05HzPmTPJXBuwad6PMbnQ0BkARkAEuzJXTs3J9BDOT7mw8scQGw43sNnQgjiGeq+fwFo6ANzzZoXZTuwpnd6Sfdes0K9AaMceUO3+A8omFDRiJFY8MIUTs8tm0Xfr67y4EkrjA4DolLaYiBCdqmr/gz24m+qejmlqtoORlzNpGDE007H8y+8BXnSMzVUz6QBUJ5CFQKDcGxarVWJhAVnUvl5J+B6qMG/G/cg1vf22Dr2cMPIhXBvQfQTg0fEODV6LEcW0s4bAAWPmWpkD2WqYOTQy/jQOF62MaOmDqCoPnF42lk8/V5UIl09H+5luORvKIFWAU9C38wvxbucMEp2r/KB4LxuXl2jpzZGNU9Uow/MfLGUWpYIHzdBz/YABuVMiv5MXB/1c7y/S74KueFHUCl4q8MiycUWqa/RzZQxxrVkWANwuQZ9p9AB9cN25xk+cwEw8boyg8EnQoiU2nFfGPkyDijQr7Ffp4f7eOrv3hnft+Kz/XG+/u28xcOxH/ReuDHGww2MHo9P++4T7TMMPgT5BIAE9UAheAlAwyQ7BdH+PcmX50G4jagoSmvZGLu+kTi3wVjSXjU2PArmborsFPOi0Cjjy4KW+/UceYw8EDChTW33EoIAWJ50xOf8Pt2z4v2ICWTVXYeUMrfkI+4IwxTG56gHGENbOgJG70ed+3eoAbTtJcex2dgSopR0z0PX84TXoOgYoRDaxtioW6/NM4X8HfP/vyRieQqgWVCovc9kKE8ckHozF6MLzpFxUJo/C1sMRxn8iGW61UImWOf8oNafH3l82MHL3J+LJGAyxdkX6YzX6QEv0imsby0gt6IJ4307GOF0sqJyFTd8xkQFB9qQIKoHIhv+4PIVnGTCN/Ir3NYrfG17hXPT+hgFWvcjc0MGgqDnqarjxhwzRwjngUdBJAE8lqng9XLCq/mEm7yGhgeg1mgi1fW45hW/a36HifRayvU44LYecF8WTLmXjweAd9sVqhC+SS9i08lU8bnpqCmXwU9QcLUOfJWZKxp7iqbezwiE/NjzEzyZF+mE35WP+Djd4ZrPkWF0Ww+4M17OmDZ8NW+4mja8mM7h3XmoEw6pYMkFD9MUIm4OBjyccchlp3hamoahvrm9wDWvOPKiKqdRSNCIsKQgrYFxzyvOli7QLOx1qhOOW08hKI1xbgkTkZqapK/h56e7EDJjksiy+cb6ovNAuOF6WXF3WrAZv0M3IduszAuSkiDnarLq2pcp1aiYe8hFQcmivK5SGMzKefL3eEOyiJDuSDwAYCJNSb4aC/6N5FNScnMxTQ9As7CYPT6iobhGTY2mJFqDKlGom/IGUOOuhWHv6MjdkiRo7k13zZMxpLFfIrvxOuzkYms2VWC6J9QZ8Mq2Yus/FYqQDZleEcJLS4OVSXuO4bhOX+iAAOZpGRpdroU0rmF2n4NH3g189/z6Pfr/eMRhd6+xlu7B2qfZkh9qn1nwEfEyJwc2Aw5iZNBhIxlJM9K/2r0jjkbTEA55IsblEwmtb7y7CeLsYp+Yj+IZ/XpxG80/7PVG+gWH//cXxDwhfu/xsgg8vNvvc0SgXudgPL29cB6CiHimA53o3x7Fh8XgP45qnRsTqHe4B+qgLcIRTd2utXSCo1gKcvS1XT4AGFlhbxGoIeHX7y+sVujdAf7oGtn/7IyrEbEDiBiVWzNDqMc9a3Z73aMy9vcJqO/ZEgkNXmEVAE4yA1jBMmE1UFJJ009PMiGhhQLmDesG7l4B95q4JT9umlqZVfUoMvEjnYwx3OW1ShJb6iTQVRf9kQzf9UwWNjfri3QO3sJ4nTqERADPWtH7nk1zYsyaccGv3XelEyQ9HfOpWP9l/5y74dwPP+fI89DxnyLt9aHNweXwlgaQk63qauaKBSq5PjHjjPxobMc13z1RcU4o8fTaROdcXM49YGNNk5WUGDs15Y/4eI3j3IRU84OVvJ2pAaz36x6WKth5gcbvjkqho4eD0DlCITTHDUx4EsSyf5esIB11Ofwdx4AGr8RuzLxPQ1gGCrhK8xBen7fxvWYpu258fSdL2wHDU44ecmNNhvUIjzhmj74WYflhC2CYaNvwmXuD3XA24BHnH9cT6evYo3X6Yn0ePQ3A43uL7tuxoz17ef/jOPWN0/8u+3M99T10UPa9ts8s+GgTw4uIscWTZAXKgYBrIzpWWDU96um4lnIuxlUI2VgDLG2yz8eKtB7fN69AcOlc8tsedqxjgojzUzXxFVjiLmMHXJJ5CSTprOyFhIabfeIFcE0Sl5YH0K1sy87ZzdsqGsfzyW8WupeicBb2yDHxjVm9OAgAtLvWoBrqhdlG4NCRsh3rL695ieTMaNtwTZdkt1iqx0c9Y0fjtoNnywAmrHQ9GTcnLAgaxm1gnVP/evBRRu9R96L1foWlIZ4yJpH1QwXdS+a3bLFQYg2dAAiCXmwsFm7YWsY7XOFME06yGb9jwtEUL73Cq4uQ/eD0PjYqDxd4psZ5sGRnqTjkLerIAFoTQ6uhurR4D5v4oj6GHABEKftT6qbOISXlEpg660QVr/MxwI9qdPQN3VNKAQUfN1m/82rW4mELlUchgVObcFcXPLQZa0so9mKuLWGtqT/aJ0IvgApwHXJXlPVsl00SFt4wU7GKwhM+KS9wWw/4xvoS92WOasBO0kzmlZlZuTieUZRIcE7ZLHSt9hoKsjaES6poRFhXFWG7yhuYGl7kMz6f7/CF6S1e8cmK6xnPx+7uvi3YkDrRNGnY6j4tOOeMRNcAlINzKhPe8yG8LIdUsKQSxebOTRVyvWaOZ964F+FhndBMk8fBh4PPsmm205wrpqyy6pfkT58rkUVj/JE4R2HlgA3hFQA7VeOQZx9CbmNa8vuy4FSnR0TjWll/Tu5iRd/AB0AQ6zNL9wj7OuEbtxlmbbYN1gw5Xoc0dPfkuBFk7TLTMjIbF3SeWJJI95UE8EpI1cJRQ/JCpLKaB7YtewuKHOA45QAIr6y/RpqhZwCNsdMyIV+HR+5hyFMgPCNR1mK8PKuhv1szfexob9yxrfHfiwfkMws+0AR1UrdPyzBkiR6b9+YbxhBu0M8lEKlOOndDYQ8Q/Bz+/2Ey98H2QR4N3dHpAUYAmu6a6mTIEQzE+UeU6Ru2M65tsvvEiweO3rd4YaLPQ4613/vuHqV/z78zoOkxnBsekyyDLK/swYn1e/QIjTs+CSCFQGns9/6l8H73FxwBBnasan8Bx0GjjrZ3XixXAhzGzf82Ahq5ENyJ69T9SxjPfABZT3mYxhZWqFn0bt0e6wIkYJISxdfa4CFwb0CkskonGfrGdGqTfperWsF27Kjr0cvPt51l6c3j/0l6BkdONT53S7sI431ZMNGEipOm9ta6659Lg58NgEQ/SCXPPV01s1roLILNdBv8fm7LAXdlxrHMQax0r4Rno3w3KqcObJrtRAmtp66Kknl1U04h2FUaRzgH6J6FlFzO3TJ9oOMRxzVGGTbYramWbGZTPjUA01VVGaskoC32PK2ooCgw2iThk/IigOixzsH5GD1CT2qe2EZ+alNIeHvF3UwNHgRjEuSk86bWp8Gcj4EIPfJ0hLctVWyNo1p1FKnzdYSG9O4IGyA8h7UxjmXGwjXSiQGdDyNheMf/EAVJ0gQteVkAQmTluTc0Omz/evoq9NpeQ2rnfR0NGPRjg0vnYdoRvPgxuHj/R7DgIf/2+LhHr6Vgf+5dH3z5FFv3aN//4eTUxAy1/ee7/g3ebvXUj/0a1shLQ+1i6jkAcd7NU973T2ufWfBBApRrQj0AdQEkA3UZBsaOG8XI/HsuHoVLFGi56CPS3TEIxUwZfxgNe5BxcbjH51qW7o0YYmdajviJRVMwgCJE6EgSrET7EL7wSUyAXKjHdTEtFUu71KIYvToanpA9YBFPk3WSFGKT1myh4Z7ivP2N45Wi+rAAMW5ipM100voIva8U52dfOFhMnMzGonUZfGLzgBi61jEzhM1qTei97cFYeLLsOK9jIxkdu4g+WBmfgy1O8T3YYt+UOxMaIOM4oI+3bwzqBVA+hy+mXsukwQXDNO4fZFAz5npp9oRNMj4pN5EBoYepFTsbF6Ong6bBld03ji5YRXH8mGJKUN70ktSDkAN8ME5F+SlNCG+WGVdpw3nKcb2HOuFb55u4jlaC9c0WeBCtn/IyZ2SuuEp5JwJ2XxacW8bdtuBUM+5WrZ9y3jKy1U7xMb0Mr3yoJTQkQtRS2SThZC/Ou3KNu7rgbls0i8W4FIsVTlM+B/didElCO2OtCop8HNeStKqqhRuYc2TKMAQvpjNu8tmIuQ2rJKxVPRjO9zmat8Izfj5Zb0K5tgjjVCacai8U+Gn37bwOD8uFmBnXkGtP3KJCrRgA6dLofZETe34CRIp1IsEhb7vxF/MChUcUBhBIAAM3yVR1qy2kbU1Yp4TbVdVsr9Iaz/dDITbn1zA3SALSXNEqoZ1Tz3IZh4b6miU0rKVVy76797lBbG0lCDdEobg2ejYoPNA7fY8nWoTYnRto62+E3X2vYmj5CGDQSNL1cLeWtmGZIWjmCrox5GvXzos7bo58sSd4H4Hdhik8jMmwxoXRNQCVuFdB0BfaZGN4egJUfUr7zIKPdKoh19oWGSqIYnCbSUe+NjA+0DFQFwgx0i69DHwMMAFTJycBcG5TtEcI0J/QsOHHxg/bNB2RD5tc70y3tMf+7rwdvL9uTALqwAMWOom87nEztReCqgQ5y/tOTTfwuFcfwyc8QzHrCUbg7emmo4dhMHx3ZK9H3gKGhamGF5qwI34CMBcnxUuwG0P/eCDkEg2Lh1lk0hR8yRiqceBli+z4ku8euIFY9775x/790duj+g9WY6TNYfVu0oHB1pKWescSQMBrgIxKp0yChbaQKF+oDB4NGbInepG38RoAUAYuBdABiH9uU0rd6EPp9ZlVXjxzRRMGU8Mr20hf5VPc08ITnqpq61yFyf62iW5yvkFeqlnOqWjIpakGRAjS2XgCprWBvf7G2Lz2zFiczUNbLuYVmS+pRHhHgPAuiV3HJeuXVIJkO6eKIgVTmVBTQ21NBbSAR94Ir01SRJ+198ebezpivGye3OSzFlWjjHNLaEm9LYkEFQjhuLH2TIwjJO55Q7L0XbKMn4brrJu8pgQ3tKbaH62RphiTepoBr6YLTEORP5Wd77VxlBTaUFMXM3NOhgy8jPB8CAVHo5lQ2alOERpikZhLXdNknO97cOTnBHSNGN9FX+NHT4J7kccUe3KJ9GEcR4Kmb9xkOQLhURhDLuO6bkYTeFhYxBMBrK/NgdvwPbsV0smjxvO4Hvna57xAO6YbzcOxvi9a3zhc9n4R6f30Nqq4ekR0CPE8AiN+WbtPB1RPYMdPbZ9d8HHcNP960UwN12zgQkHciTgWdRd6hDecbDpK7kI/p4Ke9z3sfdVQn7dwSe3iiTaJpH/UN17frARRzM3BxUVlxQALQ6niuOgIPuxexvVtd7yhbPdAaG0V2Wf5QDfGKP7mL1QhpLMCkrogJtL/l73/C7lt6dKD8GdUzbned+/z/ekkJt1J/JQGA0kQMdKisb1RA7kwoBgUIRdBBEFEY1owtCiBJiTqjY0Yo2mk0QsJiCh6EUUC6k3UJt4oQiso2CrdEpP+znfO3u9ac1aN38UYz6hRtda7zz6J5jv0bxfs/b7vWvNPzaqaNZ7x7xmggMboBxJIEGcVLIfdf80wmsBf0WTK40OllzYF2k4gRXRoNTmYiRuKzqCD9wUQfk45AZoCeb++K3qdfaDsVowt78/zMjpMLyCLA8Y/19Let8tEn02yKCufbmXUjZDrYqDDBdwuDX/d/gWeyoEfKRZb8Z3yPqqhUpjyuqblezqoDDdBr7aJ39wNQqsIeUCC5CkLDRfqmwvn7+wvkdmylxbVWd96IOyhG97VC57KGZYexnyQ3ZOA6PPjGS/NMje6SgTIfnd/8Wf3GJI2qM7NAOmEXjC3BVN6mwyQQcsOeT6Y2gwxGvurx9EwtfdtveFNPdAh+Et4a/EHaXk1Ubw7L8B2M/Iw7+tnrqG/3/ZRnXnGHJOr4uaWIVbu7bVEX1nNlqnAOSXY6OafsHtRvLOcVpjRmVX1ImFlGiRgGmCkoeDoEkX1inQ81RPfhmXBXNt4WUuzirDPlwN7GWDmnddyed6OqNYLGCjpvq6qp2EDBr6ux4azW/HC3sUCy4EAaMF+6uDk5dzwVG29cIwj26nXAKrR1yzYNAXNdkS8mlYZ+xSLw2UBrRhF4+CyQeZ9eVVIC/eHPg6zkzGyB/3vwBOZX4T3pRDvAtHBGLpa36PPWQz4cZFWzCzIfA8gOJmUlWiLoouAW9gU1Epw4fEr8RinUSyEK4Z7NWujpUxBqcMo0KH4teN2eeeeyqS9wzVlFbG02J10tBqDOAlmIKFYzq5/ntDxQNIYNVbUTWF5g8mCzheyacBqaZe7Wjn5FKik2V8IBI9ELNRGRJzWYEawnpY11STxWgE0N1LYEjWHrzGD3A4IUqoXMKFWpmZNbQlADYtBUWADevWYDvY3vUB31yJKS9HkcR7HqyrkMkzt/ajobhLURP+uWXtJ2k3c4gKgK2RHBGdNJkPAfA0ErQMTDctLevniEdYA19ToZusq2J18y4qtDbbKL51KeitXvKlHmMazyfkHniJpQtR4Pip6BE4CwCGpAmrKfrnqFoF71HqLKLrzg5xOSz5NsQwekNN98afXYHlTrRbJjiG8c7DoLkN7P7RETMSpJd674imrT+XEZ659U3PfpYe2a8eOwF3YFKKdw4pj01awuYYf5yXhvUsLnowGmfhPGBeRW1fBkQrLtdITMCuepj2sLsZV4se58OZ1GC9TpePb2xU/sr/Db336VTyVA5+Va1hm3skF175HTA5BU5CLtR2nFw08tQaobd2o800wnxZHQxmc3EVjbh1QKCK+hXO+hUvLAkvpLov17JYOAo+JfRZOLOfoK4CvW61KAfRitoptt/NPVHTpVunWadv32iKwN9dD4n0YmHo7re/HYa6ufnghuVNQbgX16vQJriTQWjFkhymtOY2VQevlZufaIMoMCPhxxUhCQAISiUzMvjCQlUEP9/RYhgVmMVAAGMSINL9qTaBquTYw9rrJApMUxL7Bi5f6V5vVMzKLz4KWgbHvnzIsL0jbnuMzlg/J4Ej6+Dxq2LT7W7zWvrng4+U6TGUn3G8vkcHSL32UXQcAlIfEUJMlweMXAvnx3c2DqQjBXW7pPIHXcUGYoMrp69UjkWXvkM3IdtiTs/WoQQDRQWLll5Yi4boIIerWh8jI6TriERSD4ZTPznHyfkQwZfon+cXgYuU45GDdhPrtZdARJ8JB9dLyuuvgGnGhHBYXWlF4/2w5iMnh7wA2hewdT2+OAB/n1nGWzTeaMh0eRGNpHDjm3es0mLsJKEdGEBgvtq+t8PUWs35FAJVKVLUl+MoBuDTRBvDoAxCw0BiFqYGPC7AB38H7O4IlAo73bcd77FEjBQCeyoFvy/sQpBXqRdoUO4x/oaLjim3QoEMiLuRwhMkiaiKD4JmMqAozyasaeOG536pXNCkp1XdQGGZt+5aCTVtSrYpKZL2Epo5hrTCBeQFJvAqsP81rALHP52KtMWE1hCmBh6U30+2Qghd11ITJbptcy0ZciGbL0NENiPHZxMEas13OZD1i20rHt/cX/Ib9S/yW/S8b4Zwcll6dAre6FkA6jm6Btu/bjlMNXBy94ta2eO7WLUbj9NiTIqaJbt63Mcc1YikiTRrqlXEHAy65YUQGSyy/J4i6lJkzhsyqm7tarrJN8R8tMtIUW7VU3a3aG2CcFwW6CerW457Z4kEgSqK+roLDn/dk7aEm0KNETZdyY0XuUUoDJYMPe0eN0TSVglDbD40RWwbP0iLkNSmBEc/HuLAtHeTtNR42xu6tcXtjf/Q/yb9Baw7dGVT+vHNOyDBbxAtMvmw5wlXCEgLKD82KH0I+hELNVgIjBe0DY+8iTkTTPtjxawN86Gdvxu/c8JN2zvL2sYsWQJMFJDTxBTnm4B/ImOxskiIfvm42WTTZZ0rZiSn0wYJT3ouL42JSqnihtSipvNsmwqBL6Yg04bBeeP8iCNIF6Cj37s/02sJPGE3OOWgp3D4feBZUqwVhtMaAtg5tBf2UIG5jJkq2DoQLpwAR/05LlN9IdwOR9alN+fzBilo0ii5FVPv6fAkE8L7KhyxiL3zSGJRdDN/tmFcWHiR1LjWXQdWO2bQ7gTzB2czt8q4e2FtDh+Bdu6CrTNaOo1ccqCM11/+VolFgCzBQ8tJ3/GVYYCc5IQ6t2KVFim0WyO+9wNxRTKi+eNn5LZnWTy24JvKqS22eHkreEBsckl79RXw7slzYj2vf8KvHW1x7NVcFqAVv8TsAvG97pK0apbmGW+jaNnx+POPL4+JVVBG08NSmWYwwB9Ty561v2HoPy8HbMjImGsgyiji+weMNzj2yP2r1jCK3Luye+WOuCwmXFa0QBChnK3j/skN7Qakd2IG9NjzXI6r+vuiOF08//rI/BSFbtsDQUnPtWwTynr1E8CndPGZZw3ChFQnXCoCwJEGNb4Rr/tq2IGN7quc0lmzZzfFcnb22ngPwisUVHVrw0nYDSM3Soa/HhtbKVC0ZdUghgQeiqhoNu2hYkmydUGuyg3Nl5pNunKy0uzu2XO2c9jyUAvE9jRYF9ZTXs5q7gyCARSgJTOpVYm/hPtx3u27fae317/m+n+lvb1RSQ5awlIYCpUnQpJN8stxksjTkfakcyS1fjAiSLu7Jkput2QpT1IgwqKweElQMfG4eMymyvKaDNwbpx94acTLpgbu5/EMZ/Mj2jQUf/fkSD6IrAlSEYJ4q0hYunJzFgcdCtQBR/fCcTVJD4GAsYBkTPIEbPJSHBhayVu4WkeLApp0Aqr2QKL6A2MmiQRlsVozEiZGevXg8hGXKSFRmnPsx/xmg4+RCt5cSD54lgj6rQrz2hxS1mixV0f3lR36BiKgFD+I9YLZ1LmRRYO+QarVeBvgYVgQSqdESkS0d0Rx4WIwHoPuYP7rpCNhiLZzjOrRkKa+FufZNrLsMPOLlg7/AQ2u+ugB5LsfE3PhUTyev0hA2ucR6le4BpxomefJ/fNGeQgMl0DCzdXNBMlweNydpYqPwu5Qz+t3bKEdfPUvl7XYL6wS1XAsWvcQznDp4MW59w5fnxYM0t8j0eFjCHbDrt0Ga9dI23LplubBKqs2/jLiKBXiMKbe/z258JgRkDDCtUBzAFNjJLJubuzQYL7GVPnNX+LOfbi269WGB4H1btz5SGweAXnsAt2efx5uzql77jh+0Z7zrlkJ77Rv2BObsWaoJ93MfwbXJ5RLPrkZbf/aC0+f9UtuQqDKCjrta/AcDbBm3IWms15TardhzPBXW2hn97N3v6/+OZj8ba8TI+nJ6l8T2vib3NPW5PSpeNwpTukLSAbSRGRKZeQLXwGW4D1xgBo8Qs/+qB9wfppCVY1FI/L3uu+1/4J4g4ztaCbKVRIrOTNIig8Y8/aNCGfXApmD2AaLKDbGfagFIoRIzJuP4+R4EUpQRMqwWgFtoFrqB9LsFyfq1070mWcetkHvro735A+2bCz6eqlGDn2lBEAwIzWUFeuowiQmiDPKjqoR2jfn4aG4xKW2mbh/nL8KoKvqTjOsobBOaCDMQAlNvxQlg+jxJDil1o+0gLRq3IvTLEK4klyGCJyKdLDzJChIkMrQIYF6ofUvuEWC4bljB0BnWau0otUME6LkMc3E3h8DiXvy6pnGouVO27pHuAtx8PHIAK0FO/A3UqtDSUFTQS4FuioZq50vqKy1GzcFYvA0wdw1SXx278GVXXkMxZzkppg0lpunEiAmScW/yoYhv5F8cT0ZY5bvT+7aHaRkArm5SBiwt90TB5/qMrgVPxdJdv11fPMDzZm4Xp2qnhv/lOcjJmB2zlYY3OKagQuOtyIGcI3Xx7X5M1U6/OJ7COvKd/QVPpeFb9WpVWestgMWhFV+cT7i6yf8mI7gxx69kSwswNFoCrqd6hovny+MphGxXBbpZLJQasy9Qc1V41gUGMDFh3iZLx9EtdZaWJNbY4TgwboQC+DwrjtIj7uCzekOvAuAa6a/vzgturaLIkwnFs5grYLPMkffnjqfTeDoKNAJ0n4qlVn8X7zwAeQOrATMIuUh310eJVFvOVS0d29ax1+7pswYQyANy9oKCGmm1fEYW4+P4bWXQpBuAqAGI2Qi+aLFifM5TPXEpJ757ebF4kNLxtBnl/Lu642g1+ENqTbFbKrhd92G96QXXc8Ne9iCl61rwwgyYZlaV091LGbgM8O91qnz/oUVyohPP729Kvwf8nVWgb4LSFHo1AFIOAyuWaTnIKMO96ptC7KGSZM9qEUj7SLgqwtpqCnJ3q2xcj333IM7M4NwT4VdcEwhXTrlZQb9e+kSTIOqF9lRmuaeIxItQpLf4yroZv6T78tjsfoZhX/21UFiOyHTy6/tkU2OPvOau0N1EdwCHtGgCsQQaTZBNYNp4wOTUiRlzzP1bAYzCzWuC2Ubo3zHwtMjd12EiS4ITGP0U2CWnANOsNEn6lz/D8ndOw20ysjQ4VppesNx3R/RGIrQAMwcgypeQc+MR0rJ1lM3IgbSnSpQZo6U3KmtFI+XMwEuTktDWGLqI1l5eYMYUh9WK8zkBtfF7WLwwHxfayCNyHz6Dn9u7BXYefcQd0ApxaMHmJnY206aHyb1DsKnHgxQXWq5iNAjetScbBwxggQIUNCeVGrEVeXy7a8o2mvYAT/UM8NG6mfhVJaVXmhb/VE4PfNWowmpkZy3M8bnx3sxqGc86AAqzfFg199a3wXnSC0ijL8t8A3hYhj3ARDqWhcnq3dH35zJmgTEzfA4L6O24ClljK04pk5UuLGgqOGgRcKCYU393L/7WYC4xHtNh64rAaLe0NRTpCZhrxJuM4M8ObnS0yrDQXAHB5ohx4XxuDiSu2OLvlZBuXE9Q1Oq9BD9McvXRSqYA6qk4S4n07zy2TMEF7B05HGjy3egQvLQd708DM2Zpgj/7vC+s7+waCB7vcBaydNky+4aPKl5XixYT5/Ppl5SRwmsmsTErkAl4ZH0ngx3ff9kX9QNC8WPAp6Tj6yJj8rLX/NwyLL/wZxGB0kQfe2DKZlz2y8jcS+4b8WtFn9LtJ/mZ+vQwqPWV9o0FH9LMfBWDUWxBYPwJVqoNs3me+GMI6iGATJqJ0oQmY2A9nkMx7ilN76yI1LanhTOhUY+P8K9Aci13kSjzZgPs+MlrIKgA5AiZ0k3F0Kkq3Bw4I+5IQeaGmGq7KIGCAktg/CgR3/3F2xBuKXHq5NhwgTCxqvg8CIBMo+6mUS3DhSFFoU/NgNjhsP0oBkx2q5FRfOwzQGP6XhSZA/zeYhao3V++cO3YOOSyMXyRaF2JNfEASGSLVU4CEH7Hr5lqxngktXFhQbbi9kgG0t36hqcysjIY75FbSwLgXbvg++cbFFF8u75M3+eAwkMrvvBU3K4Fn21XvFFz/5y94slLnVNYvC2edZKKfWVrBVNlz27EV78qb8yykNJnmZXx5XnBrW14aZtpwyni7FSbN7J9bvWI1GD73qwJX5xPUbnV/o2gT8twkOABObSgaDdw59aI2s16UESxt1Hbhc90uID+f47P8KVTdzctBhRatXu2gnZUvAD4i+8+w5vdnovU9dny8c7jU4ooLm8PaBds+6Akz5kjtEpxjK/6FO6Xa98iyPh0avGu4hlHFptyPTccKavmdm74HM94sx94qjKq7/pc2jzXyHCiC+7WKy7FXwJYUPBn283XqfXxy/MJpw4Cu3gGB5hPXqX58MKG396ueK4H+l7w2W6xLYPG36xtXx5mKTrPYkGjLxvOUvFy27GXHpwqgIHVN5sBm0JmX+G1CvpZLNg0xX5Jt3gNuua5VwY+ISu2x43Ffk5gk64VMR4bQkiTdOxOCaW1gp0MgKAeo4ZQ8sKanCzM3GMILoRWDMYXBsp5RekhoEqWdpYOies3cXeLjDgY0RmY5X0wKWjLtmSfcRioqHFcqPwVjGydj2jfYPDRJyQ5mbTiIKQvdfnM/6XMC1EXao4Mw2TGUwLo+Gddwk0x3aI7kJkcYumemqjB2dUIplO3tOh03sNiRhmZzgHM1uo4bB2K6faPxo0Mr3wuzYGoD55t6tci1YkHEjvp6P8AJCIOQADg8OM7XHALVpNQxACkS07P4910ZQ+oaa4E0KzytvQ4/tyTGTR/F+OQxjHNf+wfZYDW6QtvBAPBtaGzfz3cAd6JAsvLZ5wIs0GKKJ5LnSwM1JKLqPvhhwa5u2ns9FTRTRo6LD6AMQnUWHuaH8CsIdRw+QxmVylWME36YtUpw/1B8096/vg9WyT8RWs6LA35WAvIRtKYUwCqB9Wu5Gn8jLEOE023H3frW4CYwW+CiDEiOdb1MCvMrVdsvaGVFH9BN4aYK2T3VFLL7KBLo8/PThDE+A/dohZOzm5hjEn8XArf2bUwjVmupDuNs2LEjdAKsrzQe2kBYgHgvexm5RBaOcZ1w9ria9AACyawOawoGuN8qp1Rq6UmN3+v8jMEbbt4dWbp6EUgDrgiAJ3cSFmr4DvqCtBkFaaCl2QD9/PcaFwjSAlrcFIwp70jn6/z9xMlQjo29u0+fx97yQQGNAEQu8ldtmDuC+MhM12CJnCQ/63XiM6M7TrhnvsYjxWHcfzzXv2R7a8KfPzL//K/jJ/+6Z/GH/pDfwg/+7M/CwB4eXnBP/fP/XP4M3/mz+B6veL3/t7fi3/z3/w38aM/+qNf69rlenrRsxSZTMDAeag6rB98amrOKQ2XpnkLUhqbrW7qPrdhQeF3+ec6AbxoFm7lWoAXQK8FjfwcouNlYWQ03KRc/cIpQGq9BwldirtbklJsC+TkyzY6WIqmPHKMhRlMNfM9oh5N6QjSM9ZtImA6C85Soyz2VN1VgP7UwWJyXPQqClw6yt5Rt7FBKZklxQX31t06ZK07WKzVNbleoNrRtUIu3awNL3Wg+Ta0HvatnN69iQRoAUz+lZXedq2BmxMAuaXpiJcbAVgtfsfnMc2dqpmPt9KN+6JbfESB4u12Q4fgS2e9JDNo3oCZlsrqsb9++zKuTVCyixUx42em9ZpWmhdJdiFsThRWxIqn0RKzCvHPthu+s73Hd7YXPJcD3/LYk4vbdH+1vcW79oT/5zAq8K10e/4NwYwKUFjZwHxxPMW9rC/mHvruxaw539otLuLl3ILbYVTitYkyQVadQ2QLXhGykzJ24Clp7cxusaXQUxbFKLLWegk2zrBQiwWifmu/4lLM7cLU/O9e3uPb+wu+PJ5w6yP75f2xo5buQcU94nH+4vltAyyL4H9y61hXwZuyTenKBCNfHE/48rzgem5QF/61KJ5qCyG/lRZstAAChD5VG4dNOk5tEcT67rzgW/sVT6XhTTHLB9lQvzyfIhB3Lw2bW9YaCirM/bZrm+Jm2Hax9b47GHrfWEPH52U/IQK0s2C7NLy9HPhsv+HtNgoivjt35zYxC9iX1wuOYzPr11mAa7VsPcYpOOGW3IDtRbC9ICyR7cksGdIxCoT6nh8uc8Css2IFK++4jrj/e+G4QZVu3/UEFLKiJW3+m9dSgZF3BWACqltNNAGIIIf0vYb7cICZBDC4Z+Ump0TcXn4OWmIi04X9SrTvjIXhhXNyBfucrSVSMNJrV6X3K9q98/Qj2y/8wi/g3/63/238LX/L3zJ9/of/8B/Gf/qf/qf4D/6D/wD/1X/1X+H/+r/+L/xD/9A/9Fd0D4IPOb2y7Ume/THiDw0G7i6INE8KG0fFAUY8RiPm4asGLmvDfl78Y0TxIZCjRCVW+znuayYqnznl78uD5O8/FEXM83r6XiUASckU8g8HOCFmDw617KGk4mdgt6Jvvnxc6Pml4CGCqJxZihGwBQmbL+LVpxsFqoBUsCqdGxpB+gk8zmxaFwiXjixfrWOUxj7CDhLwuLsPEBoaUxDPpM2uwicDDxYtm4CAH1+kxz+m4wIjKyDHJ2SBT/8/gycBAyB0nbwWq8G4AKsPYuRY3ynv8bZcB5fGYi4qy7VyTMdatC3zdABIWjafB1MMEMeV57f4feb9OJe/8z2nvmL0VYEpjZOuxTm2gsRhOjJBnHZ8K8byWf3vWuZxya1pmf7NY7XMA3TMexrXfFTEY6Tza6wBjedcrzGsDbPLjQAkW1vIx5JdR+RUyaRjNiYtmEpzkCqtbLUY74dU2wcGV8pY36tFKywezowaRIoU7j4o3H/Ljdkr6d3l8av1ONwq/H0pRJrb8q5zewaVEH7/aKPlR6tFht9RoD8S3K7IvWZtyb+HDON9kny7v6ZddyLezPup73OPLN+y9OVuD/0a4OOvyPLxxRdf4A/8gT+An/u5n8Mf+2N/LD7//ve/j3/n3/l38O//+/8+/t6/9+8FAPz8z/88fsfv+B34b/6b/wZ/59/5d95d63q94nq9xt+ff/65PcfThv2djtTZOirc9l2hmyQT2UAi6qx/rK1iJjGZEFse1Cm1ytFdLKY0mKKIiohyOEBNFwpUCKfP7WJoOgdDOspEB4S52FzsNfV3CrR1EAJef/QJ/uwZufI4aYagg6imzAFUQ8V34HFxOiwV0xSOeeFKPKSPU1Hg2XLdtBXTIBxMETDqWdCLQqRg2xu2rZn5tRfcYOfptPkD29YSGLHvrFx3gx6b9bEodHfNoyvqizlMrZaMgG5kMhqGrTADD6870wRTal6AxPT4XA/8GebSnv8AtFnGxBeHcV5w42VdjVML3kDxWb1GvAbjPoY53y72rpE34xkVHW9rMsXAA/ScEdOO0yiq9t7TYQl84vss6NXASFEzkX+2Ge34xbXxq27oTaw4npToI4Nlv7O94Mv25Jk8DGg1AWbPbbEDVTQsHHQRZEBybeYKuZ4bXo4tWDLJ79HOin5m90zBqU6a5RNNErKjlNDSKcBG7M2wBny2XyGi+Mvv3qD34doBgFI7Prsc4X4idfkGW4dns9RiVt+lsKzFnovC+8mp6X9dslxZtdqniPeghePaa2R7sJ1eefeWnpEuISt7f+JSixF1MagAwwUz1UnRVBdHR7wOYKnIDJAmoypdfZdSpvgkpnUfnl6xgiZggD0jdfMxhYY1KfYANRdWdheS14TXJn37cfPida7gFZJ8IQnSDEYciMg5Ckf2i444NyeqtEWptt8x4DOxdWrKBBSlcqPT3sC9XQUjvjACOjXKPBSP/WjPGlmHDP+DP0e4iQThEp7KbywAJOQK9/JsIfFrhDVFTRYEGMN8rm5YrBhD+VUqiH4uQyXj+hzzBmj7ePTxV2T5+Kf+qX8Kf//f//fj9/ye3zN9/hf+wl/AcRzT57/9t/92/A1/w9+AP//n//zDa/2JP/En8N3vfjf+fe973wMAaBn1SkIQr00xwUUhUiTye4DEwtCQr6Gv/J6uC52/z1aUaFyc6doTiOB1I11WZqvFRzZZ+vcIVN0h8fXBpxcoo7EHiFdlnOYLEQQIvE++VwY4cZ6GFaOUbgs9CW6Ia0RezbSIaUqljJ9xD0ask3kw7peQfB6nfv9Iua8BLpZxmceAAFPi97BkUcNImsZq6Xik4QKITfhOQ6eZPWmdAMKEz3OYMcF0zRzrwPgO+uLHtYc2H/eCRqAs2VnXoFjjyVg096xVQ4Il87XGGBgGjNI19Ro3CNzi9aH2sMw8RkYQgCkTKJ+XLWy0wu21eSppmwBIJmCrMqwdWxl04es85wwSNpa7N6r2Nl0/xz+81lrPNXlybEvxomwWxHrr251FKFuVWPyOdPyvWZLIjwLMAdF3cTc+/9e4bwngkVNmRXSkN7v7bLW6TPOa90/g0bYecRrhguW8ZovDo5be4ai3FdbxOeMya/3TkrvbLzGUSCzHZ7DwaN9GOmH5nPvTfNz8a+x57APlTfoshpJAKe/Xy+DeGeSXjJs72fg1ZNnXtnz8mT/zZ/Df//f/PX7hF37h7rtf/uVfxuVywY/8yI9Mn//oj/4ofvmXf/nh9X76p38aP/VTPxV/f/755/je974HrcXSdlScZc78eLo5gk0PSvQFBeQqkHVGeJznPksSIGgSJrdY6w9MVQzIjGvCYgt6BeB9mmIyYgHavYigWUU2iNCy2S5dXysRqvP98yUhoEnPNnyMaZHzZfRjDJXK8HmGdUDMSpRiYezh4DZwA0jBYSKKUg2Ot1YgUDBnnYu57zrQPxLwgAGPKEVeELVvLpeGy3bi7WX4gI3hsOJ0IqNSumXPFJilyFG5bjoq+yqmsYzNQwaCN6pnmeNsCEA6JlKgDHxDy9m8D6pAkdhk2inopwXsPdWhcZNLgcyRLPpFzTALkO9s7yeej9wyyCDwOLVaVkTfJgbVKoof2d/7eQXkjmDLwZkF1t+ncuK79T3e1iu+XV6CFrxKx5f9CU0LXvqOq2543y6TlrpJCzKuzYulsZGIjM/JfmzSI3PGrAfG6aG+PmpVXC4nes/kamNySwJXz/XEU0plNcFGDf2GKhak28sZY7aVDuwnRKpbQApq7fj2fsXb7YZvbbcUYGmLoUjHGzVyNvJkAEjuBh3Wo77h++2Nr2W6mTq+Va/4VjVrb4fgB+0ZZy+4dovLuLYt5ox0+OJgHLD9ieRwtBiwn5/fni2F1fv4ZjusL25VofVodYcdDkTObhaYPEdv6m1ai2c3kHvG/PcAMd8/nnFr25RizTnqVQJQHK3g5dzwxfEUxzWd+Who/epnsZg5d++S9wgK4LSMkb6LsYen6ufA2CtHWQT7LrIhT2P+rFcMqwV8rzhhskTGNczCQCXI/g6LMxDZLcMSbt93Mpv657xWL+lYCvdsXcnCnnsXxnXzz3jm/HfSD2NvLAiyssioYY2xnLkjQ06w5SKiFkdp4RCFBI9fw5zxtcDHL/3SL+EP/aE/hP/iv/gv8Pz8/HVOfbU9PT3h6enp7nMt5mrJi2bytwMDFHAxZATB9gBV0kR2hywTWo6fBBB+O3ltgDMoSJ+Nfixw0hcFF1MAKCw/daDWVcGfni9r74+7N6HcAY7sZOWiEyTLkQdqeSZAZKRkLWSCxrDgrSIRQyJeaI+ejwjuS33OL1hOGbTx1slqMiwtwLBf3o9bBooxXwlfBcj4wFjl+cygbhxoay+yfNR2DGpxpLTOVNIArRoNRZ1bgXEcKd4CQBBk8bviAqWpm8uz9SBZT0bMgHW6O5FBSSZxBhXyeFbV3ctpDKFh7ZgXfJWOohboGEXAoHHN/C+7eWxezdxelM9kgOLE/EJNlp5l2MMygMeWJHMpdczlqHmtcjcXbLTI1dIjvfaNpySznw0uDHXcv8h4Fhtbz3BarFA5ToYVbcnxkQNj4xi6SkBqdQP7pYz78OetbcPdsjwb1+LZx/zk744HVieLvTB68+LWDADY0njmLBq4uySvwddapLrTktIHZwr7qanfrSXT5iubmwqAagK1M9if+CAH6xN49HG9HD+YraCPrLdM1WcpeRpus0XEc/5tX0/90AVEIB0+jY9iet5s/HnYVsV16cp6nObnfHTS2sc8Dh+Y2nC/vNrR+/a1wMdf+At/Af/3//1/42/72/62+Ky1hv/6v/6v8W/8G/8G/vP//D/H7XbDr/7qr07Wj1/5lV/Bj/3Yj32dW6FfCs5n4Hz2ioVb0uRTo/AMrXTNavCBZlwILQcU/BPK8wVSPA2UFOThN/RyCROydKETBcg4+NkdkBaIAR8/kQtNDFSVcyDQfC3Bg2v7T2j6OwMY3prj4jns7FM5AXSnKBa/mAO8qVCQisVzHMWMRHUUIlPn3WAKXLxoVYG9o745sW0Nmxc66r6ZMKOlFFhtlw+Y1WmuFSAAiPDl8c2DWS8x8yvO24Z2IUg/MQBmrscwNBBM/tFs0g0AiwEk0Q2oXU/zmU8m7iq49YannHWSAjgnczbEK6AayKjS8dbTvt4C+KI9RV0U1nHpKpF6/VSOScicsIqIPQnIrTR85pV36Wp5dhbOXU7c1NhBD6ko6OguHEl+9t3tPd61C65tQ297CKKLM2jm+fv2dvXfewASVt+9Ms6gAWczQfS0n5EGe5x1FOwrIwhzFvYrsFMU1RDUdF3luimZrhy+ti5PJ771fMWvv7zDt7eXKdPope+DCM4tDxs6TpQQ1sDINjl7jcrG1gcNF9mhNZhNCSJp8eC4BK+JW/5uZ8XtuqP6+8S1dW0bjrTga+kuGO2zo9UgR9tLx74dKNKjYB50Dt4FEBknW+nobp3apN5Z4nLQNN1nzMDhGshZThxn/qPbhcGxt1ZxOzeczavZ3jb0VsbeRxcnkp7p72t/0lFSPu239YqwkMb+qAOUcH/sG8wikFJsuf8VD1jlsm4XvxZpHPK+K27l4HpktfXFXTH9xOhb7FPJ1RNBsf4MYc3hvk9xkqwmUWWW+381i/Rwk8gEdLJlRIE7BVvGocMa3Oc5kKZWtuIj29cCH3/f3/f34X/4H/6H6bN/7B/7x/Dbf/tvxx/5I38E3/ve97DvO/7cn/tz+P2///cDAH7xF38R//v//r/jd//u3/11boW+CTqDSiseRyEDQ+Bh/p4Ce/0cQJizwuykScgkpDf5s9bbLohTZSjjdh1fBBlM8IXx+8xmrwf3kvkZsnCNKrX5b+Auikdpzqvw4FTLGe8wrV27LC8GVxicG2V+ePV7SYyVGpHPCnwK3SwjcCweS1zTU0XZ7QW+bCcum2UOdB3QPGo7AKGddiKQDBT8ZQggwPHm72mdSHre0Fw4nwtofPgSIs2jJszn53WdNcOgtnazvT17D/Irgg1gcH/sLrSK9Kj1cvQ9ghXDNM97UBhD4vq5GUnUXJF2FxMSrLBbpONZjgAhdGEAwIsLSlbfDa4PzM+Zze25ui1gm43R3AwtnXEBrzVqxZM1RYZlZ41VyHEKO+YYjyKj9gqzLQCktN5hAxhZRNZXgq6tNDxhuIGe6jll4Nxk1MUxy8KGKh0deJjpssOuS/DIeJh43tI95mlYCHofNV+Kv1uP4l7IbEvyNuFnYaEo2EsbXoTlGivXR2bmPbUmt4vV0ukyZz11HbTufJ5cv0f9GQiKWazvdHcLn0uqhqKo/uqH4pYEZuzlOt5bFX/fSwIseT/gdsdLJZcINw+FDBIwYLjpeQGSl6U+c+/QmmpLAdHfDFbi82ny5j9FR1/vDPwyPtMsZLzDBD+hTCKBm3Q/3iP2zNwdjtMrsjC2zNdf5bv2tcDHt7/9bfzNf/PfPH322Wef4Tf8ht8Qn//j//g/jp/6qZ/Cr//1vx7f+c538E//0/80fvfv/t0PM10+1CK7ZQd0MzSZ0evkwwIioyOqtlKjTz6rOIfFf3xicu6zCTJKESLthITTKE8TKs7ISm4Jbl50UyzSeSKn6oIyywq/R7ofEPwaXDhT+Rq+YHRN8XkdGPRLj1orCjizKE/EdA7HWRSzdWjtXnTAK9Lsvqk0Qdk6pHRsW8PzxTRxAfD+sLoNLLCH3aLfv/V0s0JppdkmnUuJOwAppQMbvIKmjvlyrQVe++aurPMS2zFZz5LnxqwkDga7PZUu8UVwi34AkAfjQ7AUGp/Y5vvk2R+m8dmrx7LkFJrf2V6wlwPfre8i4BQA3nnMxV86PguLB+MlyHIJJG4PGT55wIQoMz+owQbQcXfLs5z4dn3BZ+WKZzlQ0K0qq+5417+Nd+0J329vIp6BIKirYJNRb4RxCFjM8JfS3PpRpkyMta0xV6WM9FGyr3YV3GiBcw36UKsoDHicSxEfc3tWxnxcyomzFtRyQe+Kax9l5ououSLKAIS7W512GCfGVVrsKxzLd/2Cs1d86TVd4PP/rl/uU5NhbrdHVYLJeFrUmGHPUnDZGnovOIL7xqq9HtUAyWptymN+tBqWHhHLbKq94xkypeMSJHIt0oKRU7I5toDF7bxvO97Uw+ae8+SxKrewEHVsxbKBJFyuA3gcpPxXwfXYcDtrWEdrtU2ud1c4rjW0n8i8WIU0rbYONrQAQfioMizL1o3BBZJoCRQYbpqO4PJhDatJBgHDRU0iQzVrPSozbDQszVmwGxh8sL2meyAdz19Xoq/gLPHra5KPkRjBZ+T9UlxK3vN5EzeKjb7woLwXErCJZRmGvPjI9v86w+m/9q/9ayil4Pf//t8/kYz9lbRYYCfcXz1mbYr9AEbEsg/OapkIoZOFRUK/OfAzOCuKk2Xl67ALPfcncebH8QmqgothrJq7PTeDjDXH2s/NVpNpEawCMCHku+vzZ/GTHsSv3MW8OE06AOfa6P5MdeTh577CxnPbRp6/DaeiiJnPr20E07HlzI+shSkQ1U2jj1wDCrgRZViBaBbkuFAGS3o5uB5oeeLa4R6eqPvzsIUlah1fdjRjymS9YXzFJi0sEF0leDfY3tar11Ax60VHxaFbUHIf7jr4/BgxV884cPEYDDKAAv3O8pLBDD8ndwgtH7RuvGCUfG+wlMu39QoWlqMmS1pwBo3eknacGS8N/DSQ/yEHVlqQajch6xoxNeDjqOjtPoOGz8ZPw4pCSwXuNXnGfMTzu/l/2xhjM9d1YZXhZzni/GvZpxgNzuuT25sbixt6y0CPFqMpFgQ9rn0ka0Lu4146ztrDjZSDMvkMbEytflQJuHUL8iyieDn3IL2Le2HU+Ylg2tJmQehjzwyZI/WXNV1qIiG79eoxQu5ySzErXRHur9V9BgDN3brd0/bDveqZgtn9EFZQsb0hUucBADLe1aSskmvIXxeTAeteWgCo3glnu8aKfBDWZ0vl13Q/gUCHJTy5TCZW1HR9Pk8olsv9w+Kdxy3LmSwnk7xkPEpYk5ZnyNeO/hHwcY/jOKUx71UmZf+r2l81+Pgv/8v/cvr7+fkZf/JP/kn8yT/5J//qLqxAOS3TQw9AfcFxEfR95G0LErrjwtjTHBK0ZdCbBbdTfqv7DM2+D/QoO3/fNxNyEueMc8cxYc4nwgQiqnkyuy2CMEpEO+Bg1suI1lruoQLWFhkP+AB8+D1y0Gxmgo1iKA44uNj6CcvqoMnbA0h7ZMNIuGMAhHvk+XLgsrUAHgCw1QaRguthgKIUe3maikWMrUOtLEzFTZXAQ8P0o3wpwu8By6t3ttYuqcqvAxD6R8PEelATkJhzrokJlDzYxAZYkxmIef9ZRItWB9ZWyUKfrpVZGI1S8d9vb9zaUPHuvODz6zPIhTACOq0dWlAxCLmIMRn7QKHF+7Pi6rMcuOmGm2541y/oWvCt+oKLnPisXC0AFhosq7uYIMYJvMgWloywUjj51Jt6WFVUr9i7e1Xfd8XKy787L9ir1UU5esHtNOvY7VZx3jboaZaSR+mnm7tPzl7RU3XW4m4jNoLall4KIxNTbLU7wDWYRpfOUznwttzwnfLeAki9z4eaQM1uhedyBAAi8ON808LBuBFS00fKs7u3yPuRi8FZ5Vgbl1q7vw8a74U96xDoGbxTmCvM3aXOEwKMon9P9fTMF/u7dwctDhw6zALTYMAiW6zOBBzYnrabs6P2EdNBgOvpyI1Bpd3iyEgsN21fAuN4aQK9VSNsdILJiME4MWqxxHtpWrjFz413kzEd3CaoYNJloORZ6gOocE9mHOGdyyZbmOHM0sXlEokbc2NZe7+fCoKzJCYqN4KPbfTP6rPMx06yDEkOUlb6tabrYnw/KU2u0OWYExCcURb58bolsOcAZ82O+VD7xtZ20SI26S4oleRiFNaPHjIL1RwUqjDm0dVGt0BJIcFMBjGv3QsDTKhQWAlGJsaCdHIEdJychOAqd1Xi8/GdCfv7wNSFFtg/D9ObGio1gJQzM0yIBzW6aAjfGE/AhHzRqH0Rm1oKMh1R7PxpLoHaTQhx06dfdzWt0/ebN7KWtDgWbTNLCwwo0cTK/viLoxuM3MzHLoJE08TZJrCUk85douZ0NxYcc/+YYDKBTPrYlRYimKDbk3BcgQcAz3yx6xphWMo4AYLDoUjH2/0WloW3ThBGM3k8gguiE8AhNbIWALPAHNVAxKHVioZJTSBoaLA3HQLzRTdc+47vn2/cRXAZZdvFybho7YBlwZgGDRS1Im4nRqoms2Ssv6b9Mq102wS9d8ug4vgsrbu2zVTXTHLVRbCjWRVg7eNzLQPUKl+hsT+cUf/FrBEvTNlFx9tyizEChmXj2nfs0vCXymd+rIbbhQCkuutr86yfR5khxd1K6MApJeI7csaLuSS6uS3aoFPfSg96e7rkDqkQt2bk+9HdtcZk5FpDcazHoHA9zP0dMTjBV8L1jDEXR6/hPgUMeEjpyEVQNT2nsu5Tl7lAmo73ufO9y1aLxULcNyTlbuy3fM/CLcEAVPaj85i0cXD4ghk0d17CZfNaowIsfg3BAEfECjk9d7LWJ0tP9IX7OxKYmG5o/4qmfXBRevO17NnH/fPfBB4RzpA9DwQj98v5g+2bCz5YNM2FP7k+pglZzyH6AsIkFvVRXNjksacwIWiIXOdFy50Qrqav6CrVke4bBedSn/KcTIuEyJoum7VxAQaluM1wJwFbpt69Ay9Jk/eX04BSQRSV4/N7pd+Hbw61BH/OzvoG03NYv7LlhZpN1+aa1zCn500IsJf9aMV4HrK7Rbnx+t/ciGlhYLxNntTi1rLiz7yifB7qLj2tcJPheA7wRUsvonITqzrGNL10sSZ1BPgBiFgC1jOhIFotHhHMlzRiANhhWucgcTJh/a39GuDjTT3wpt4m4cxjmZEAGN8GG9k+Txnl35/EM17AQNfBFHr1QFNq71+2p8hWuaUSyZnvYupLrwaM0hqhm4OumSwct9Kh1YRsR5muBwyh2VVgmDpRy3v8xw6giXpBvFSQLoSiTAIvAjoh4QYp2vHiwAICC8itFpRbYfPYIPhBe2OuJdZUcRDwvu0Re0JSsd2Dkl76PoGQ4hJgkw4UBONpT+9B72IF2lpBKx03d0k91RObNDw7v8zN41Ze2o6CilbnmjlHcmWxrxzDu/gRX9vZarTOB6nVq9xvIgx6ZXyH60vDgLvMQygafM8VUaICCujuZzKGQR8AD157dVnkbBgK7yYoOUvD9821jZpX/oFrXIsO69+lX6c9yjaMiA/htR7E3IWQV9wTWoYChZBDmYMjK0fSxJhc5e7r6HtZvgiuFJ2Bh5Ar6hHQyWPxEe0bCz7MZKaxMDpgJnrBiM8ABSxPGohxcmUohq/NjyMzNsBFLaOSIRXEmBkHFlzgbnoK+u5Y/Lxd4ubIaJ23Z58VZkarMKGbFwz8BaRlgqhZvfMOlRUY7g6+NGmVPtgLppXH2jPluF+Zmi8lBqEjyFRh9Oi8py7jpRYgWl5ZjGZCRlCp1zLqaQCYUiEjvVYl0nvtPjCbLQeCY97HzzAL8rGSFsRg3GyGlWad4suXNwLl+stjyDFOSuHTfuCzyw3fuhiN+q3VIBijKZ7AY5czXB4WAGqLmS6Xd/0pMkzM9eC8Ga5FP9UTb4pZPo7FRLdJC0EM4E4wmKWlBdsmQF6PigLBgTm9skjH23p1gWsBkv14xukWjg4JQrACxcUpyp9wBlsos2zsXgWndKPzzoDd55cFBunusz47cPCdlBkUZy/ohSCl4ym5NOJ5F9WQ8RItxR8drUYcA1Ohs+sk08wfqPh/2rdsntoTrrph82cjOyzvkxtdI9VVdqbtdl9kezEOmO/uFkzaVawQXrH4lO6uoq0asyrfm0zRzvlgZVm6/nJmy+nBrXCq9Vsz61i4SMtIa6Zlg2vQ0rXnujEAgi+GxGPv2z4dw0wWIxo0l2gmUTPgYcndkIKwUmTl6gEwCGWLf/IcvrN9fL5q9EDan5NeFVsfgzL7fE7cx90PQedApSjv+XRjZ4LL3Ge3oD4w7sXz3TXKHpd5OdYty8UpNoUgZtkDJwAlqX9pX1OBJS1wXPmFu1vMuvLx6OObCz48fSmCTsURXAEUiRbZJ5RAYxUwvSJMa2xKDVnvF8M8+TqO9+tmjg7p5n/FckoIJ033rYNFVdWtFjyuA2mPjIhtLQoLU/JFvfoeeYl8zw6QiTSuH/+4WtMCcWQsHijHWJNprPgPsyAP4EGiHj5geoHjOprMx0CwNZLtNKdSDtP5WOCldCjqVAuG7ix2VNiHZJXgizZtLvk8uf8XABfpBYvzMDcf0qCXEcXzfuLtfotqrQX7wn0xLB7k1bj4hs12uBAho+hMIKZ3wONtuUXq65ruuDkooSAuolNwI+M/qnhxLwDFH5QuIeOEcP990QA6X/q8kSwr15KhFm2AiwXERnzKFv0Zzz3K3JtZmnTc2WXaVKbgUHvO4VZY+Shea1PqqtdiInU5r2XWjRM9SZIqHTefk++fb3FoxRftacTSYAAsju1rLdPnX2WDv/g2x5up4++KxcSQ9bUUxZYK2s2ultVaIu7qnIEpeTZYO8Z+3+5AhQW8DjI6iL2XBffvQtdRC4ZxAmu6LoEHrTituOWKLkrJ/zSs0mF9Bh4L4tSocGR9aFb1l73RL0zZEdo+lTu6Zh7dKNfMSjLJQI7E9YUW40VBivngnwUffr60PUd/+DeVYgc/YchN1XoJSoTPXNJPzHJykl+rErYMg7nmZ8D1Ve0bCz6sQJgkWnWgPT3Y/E8AGARaWS4pZpQKJOAhy3dcdC0BmUw8BcyptsVjUApeYV5NCHP920FRblMMx/IMa2dDm+ciWgSsNKTYjtR3ALiWuHaY81qKfRAZbha2TSFbR6n+EBwQ/ozCfjp9rkBEtFPrElHLXMsARy3NLgsYghUTQC6stoYTQGeacC8p7iONcQxgAk8cg+6bQjwbAZeff44NIjQuvrAqyC/k3SZQxlhkAUaNm3EcGXjY9wWf9wu6Cl50hzFkmrvkqpsVkEtkVOTTYHorgAAe9/dDWCpyJseONlmaCCaytk/eD2r7Zu3YcWCk2r5vu9Fxe0wB0167Ct6fplGfvRj9uVtC3icukNMDaG+9xtIvArcEzi97tlzQinP0gr10XOoZ9PI5sJaZOlU6zmKcIs/1iFiRWjRI8ErpeN4HLb6Ny4YX1TkGR0tYLZ7LgapmvWlSAlCxwF2MpzPHcqzNWnLxQNb5fWCFVwtOHcGn5MtRFTzvJy614VKaA5C53wx+PbUE0BhuFqc7Vwnq/9VVRk6UvTR8looaZnDL4nV2zTbxyEzz5sGpza0dANBbQe/qoA9RdqF3i2vRJuiHBZoy5oMuzwEkYHupuxRim1RE6uew3Nrn1kUBbpj2zIiH4F6a9k4eNyzkvF9StJKiFFNJdwj3INWgdY+WjuWevn41ybYETmjFWYGMWW11vpZiUP8IZsC0mHJCpqwgaJWDC9CYLCgf0b6x4AOATZybdPqWslvy4mOQIQcjAYBYP9NkUxqnYwXhNoFS6xWPtUiAJ5n7YiHkCcjCfp28Fe1MprCEiHlaBjKC5W0Yt+N5RKTZRJjJtAwJK4T7Q66ASDdFeqGmdN9qRD8QxX0v5nGkoM6Bp0yr02mDTdH4SWOeLuv3C7znfA+d4xFzJvPP8chjnhNAiTGVMdbyYN54Sb6frKy5PvtKF08hfJc66IulQaZlYxwPu7tZLsEvkSvXZhrsEdw33ApZMPP8SZigBakZBSePMUFs5xF0MOaDVpnm3ByHGM3vqJ8ys2MCCDeB+u8v20jbpZWE7dosSybHyERFY3x14zhnlxb5S7oIimr8vZWOBsvEyIX2KsFtnWMWbJ4kxiePLefSAiwTKMIAg3sZHCpG2uZWgLSGJpC6gi0dcSrWz7Hx7W7xiCKM6R8Ap1O3wNUuXnUXc2ApMLuvaM0YVo8eQDc/VyseR+TvUVPBHnFMOgFdXl8xv/9dBaKC1m3Om9MWq1otF3XQgeSq4L7EOD5uN5OrPcVGqKT3NSth3CMF0BRHKOm4ATbSd2wy9tuppX1llTnqe1Yojo/asuDDkiuLdSWDImAGH+zXnfzBLO8k/cS47h3weKWv3A+n73+tgA8rCb9osrmlRZL9T0N4OHhYrmGcFb61KQaduCJSuPoFBg4IPDgxjL5GGnP/TNwCku8Tk8n+5plJL5OZFSUW6WRFQeo/NW+mHQOp3gki1mIyNQbytucVpnaVcUm6GALs0RR36cCu2J5PbHu7s0wcRU1DedkcdBAam1vMmCRtszs8g+DOutHH6mfVS37H4DOjZbfy6noW6M0sHnKTcBmFay2vCwcd5XgATtP8RVVfXYAfP+a5HNM0fmOSHLjBLD031+gBRAzBl+fT5D6hUKRlgRwaJJzqKvj8fDMFSVpw6YEf2d5Z2fZ6BSvN7q55Hn2brkWB/BY3u6d0HEz5hDNqQvHsqaW7nBOwualFhWTSrW/XF1R0vN8ueC97VLPtKtgwAjiLWNzCpVrKbQ4MZRYFS77n1pyKPzNidjUa76IaPBMUvi/njo3xIwmEZDCyS0MXcfrvYX3hHlpkALbT4ziey+FuJtsqD62RfQQgjb0Fku7SxtymANjvtyfkasQU0JkzZJDNkTBtWJXY2D+CNAYy01WSg2lJ9rVSyVexWBGeR3cZx4TXYor0FPcDukYNWFy9CF11UFk8qIRp4Z/fnqOoHYDI1inFTK09wEYZZRoIOlKV2SwQLe1UAsTV2/JSU5Hz/S4rq7Tw9qe5wCaQ9sKqwf2BLh6U73hddcgb7q05Di72b6IdTEJA6VnzvTzu71bsKcaC59R0r3xJ/6UNbO8HWEdKClZdwUbISQEUcmc9mfa+tQ0sGNeX/ujAD7dvLvjogCxFzO6ASAxe+ntCeysERSzKKTODaFQ5iBmtpGuvLa0vTeb8bP4bByx94Ec8WIbrxgCVYiqFnPqeWfpiEbwy9wE8MrLFR6LWqih783oSsx/d0v4EPbI0cmf8kjJ89bQG5PP5M3OE5IHKwKM3Bx6nb0gn0+8G6FjdIaGIdJlz7mX+daoU+YFxlPUZX1kTZGXlps+CWddeUcTcKHQNsFAbgAACmXCKGStTkTYxJlirOnviQA03ToVGTEZz9Y3C99kp23dpFuDrmRxstHjMFhXX9N3twswZ9mUvDddesUnDiZFBQcFYPQsiBy6SZGw10me3kM3/ADGrZSXPXwAYNcC1wwjXyGz6iL79UZpr/q75taqOTKQGCWCXQSPHg2ObfzYHgeT3yEHBOS14uj/MHXLz1GrGbcQzTxatxV2C2bI0u3OShQTj9zzuDGY2yv0+gTQAc3Cyg2KSjeW+sObQsYCfRwyY2sXea4KNxeLxyNpo8X0zMJnkg5+/1tySjjnIMptJkD8nGDGKgdg/KW9CQVniKfhLUgpzBh8j8GOPiv1ZIuh0ek483may7LvjExFY6QxN13y03Dlu601eezU0/cgyjXO0zsFXtG8s+NheTjirMcptgIKo9cKmyzhQgC8LIkhafGQjSNUtD0GNrhgMp1xwEVAZOMEvHl2w1sfH0wJNH04BPPybJekndJDAc0almpB8uhatIYF0ic4Javz9b2UuLsSX0+JE4LT2XrZ673h6c+D5cuBpN1HB+IymAhFn4CJbKvvl97LAslFEimCCFg/j7PDy6dvIalBYMNp51kE0FGZYD45tieHQNSHluPU0/mKxOT509yCLk7X0PTYrRVjPGPwc18nmXgXEheXRKm6thzn/aKbhf3E8eVCebeojHqAF6KDFg1TWF6dkZxbFqV6wTFgU7sATjslF8qL7xM3B1iBmtSjv0VGCTOz759sQljyH1g8K13f94oGVzzh6DTrxw1Non+uJl+YmfulAsXTeSzkjLuV92y0LIgcgUvtNAjZnu3CtjOMMUFFgMijzdGsTOUW6ymQF2UvD+7bj2nd8cTzh3XmJ1FOJvgDXVvGrtzfBg8FgXjLRZlI2Eq412JzTTdYheNcu3oc9LAT2ygretx23VvHl8YRTS3B0cI5v3UjWPr89TYHazWnga9FYU3RjbU5cl8FC1x4ZL5sDppH6PbJxOD+WqdIjbfcpxZEQ2NEKFzElvUSg6q0M6xctYYwFYszXtnV7t4/q2v+iCSQlMIQqrcinzErapQM98R4x4FIte8+x9niP/bsO31NpTciggT9a+jzRl+d9mcrjWv9KugwruGCykupufSaHib0KMvaRpZxD4KMziYZknQYQGZWRMePjFpmSGM8e572iRK2upFeVLo5nhxXPc1I3rEDxA+0bCz7QdEZR6YFzk/RzAm+aFhZRLNJg5ksnYTItpITsKKznExHrZj3lrn0EIqRFxrqdkE26dzYh3rU88fmd1nEJkvEEoOHLrogidKD1RywldqsWYxDrOwYXyfznF6O7CrZhRZKJfz/y+DGNJyvWxnBNx3mfNIHA0HgkEKGKxBznhbH+fYfs18XzaHzjvjKeN+GtR9dYfdwMADy0RDBa8d3wiM16lFkHgL3orN36j5xBEYGsblko6hwdkERUxh3LgzX9mIqRjWGZLja4BQWMUKMl5uhbxKDcugFQWmaANcZkjkEY4zAKic2fz5YxAK/7xr+idS50AE3HGNtzFJxuFcqppwDC0tJ6wc3r57A9wThQSGGf7eNMa6WliUX3zl6j2uuR4jdeTnOnXN2lEtaHOuJlbr3ibDX6x35VpqPCiflck2bcCxstIJyHKv3O6kF+FQBhkcrxIDGWyCCxhMUjx/ucqBZEigwUR+xTnt+ZTAxjH7jbb3H/riqRvn9XFH1zF1/aH9b3PG119/fI1xbFXSpvGtfoEvd+7lHpUGZRhnL74Dkoj6ZnfrDe41F0nGc3SvdMSi8Ud+9RPMID+bneNyvt2TqzvrKSj9fYgh9atl5r31zwITKCTS/wiqyIFK67lgYAwLCOMOsjmabGBOrd+cCYzEngLy+GrBNJIZeRZfoOefGsgpF/BiW4vVyRMrWUV1AsG3MGEBXo2T/oL5KKus8ynVcUzVORIzqc5Fqp2Bb96rdWo+4DU2SldJRLG9VxhWXv1fupHihnwvF6yKTxSOkQBznZnMz4j86Xt7r5MwMQWqRoyqyatBGYbxUYRaaqRhrzBPrznPA7ahELaKGZNJtnkU4HLCvhUlsQTgHbko5aYx1TaGRBlWuyMFWR2uS1GSfGu3rx+IERJPosxlL60vfJRfJUDg84NaDyEsGtxiHy0vfh/ilWF+XqabW0hPygPUfRs1Mrvjgv4RrI7gOm0lLg3PqGIseUskniM5Z6P3qN0vG5ii1c0HYX0DlehI0WgDfbMYJZdQYV8Oe+dQtuvbWK67mZBS8FuqIXtG4unJe2od/e4qUeuG03fFZv6HUIeLrNwmIUKas14jmKdKuQ43P9Zd/wcu54f+5W4K0Y5bhZGoaLg4BERFHFxuJ2+jj3ApEWVWqbFtyag43SBnOp9/NST1wwu7Q2t268qQfelJHJcqjxfPzqYXFGzE7K5GGsLfTSNrw7LwNgpDULwLKX3PLR1KylZyu4XXc7/kgcQXwnzzI4h7oMHiUg9i2zShgAURHbF55b6Cc4zTLat4LJYxR7RpITDZAqk8CNWD1aj7nluPU4BGySA4y/02rXJ1uBcs+qCC4ni08bJIX8GVZzHftKcGfw2nlBL5ksWX6xiHiAhmwhX107jP3jIS0OvVOqM+gKGSRuWQ4aiI9HH99Y8KE1Pfoj7fW1Z+TnnroU/nwK8sk6wOhjXaS7D2TXV+8VyBWPv5+6yYUhr3d7AjNdrIAbzXy8Rr7w+syafk2Br0F4to5hupYCUbmRz8bviheEqqWjhrWjhpBgTr4J5EfWi/sBXAvEPSoHnh+VAj8eBOmFQ0Lb6brKfum4EKPAR0nusUbu7qtLrwNcavw9/UyNgYtjjB5bAAwMWEZGaMaQiPHIxwLJxw73sRfFjtOyLbTgwFy0jIGRU2yBmIBo8HReP4Zaey75Do9RaPoooyVruSNgdD3ubmygU79oulcMS9mj9TCngd6TjsUzq8T1OYZnr+gibpEow5WBPPfcqf3Rk8afYxvCwiCWIjtVpsU8Tpy3KgqUhq27u62WaU1sU3Dq/DysexTB2QVRE4XuzCqYrGWPrpPHMKwfWNalIqxZZwA+y86htep00JgzlNZgYfZ7jPHIXFIVc6MqhiIxnTiE/3BH+wwlAKIAon6Kp9pKscB9LQVdusWR6NgroDJ4y04MpQ34ML+RjA4Y89Lcn9hHYMfexdO5tUa4ifDZP7YJx276cwCyJaOHB00y5dHe/6Hb5fM+piVA9rHtGws+zjfV5qcDcgAFgsZy8JOAs5+D5AmBcAHEE5LLIjN5dlpTWEOGXwQaJMRbRpSIb4GGjzBBCEkukC0tzgQs8qTd1ZiR9DlwxykyaQj83vtpgUcI7o7IUee5p/jnuGu1Gu/BZ/sNT9sZufoAcDsrzrN6sKgCRYYg942yNd+csgmWRehIf78AFg5vTeXDxcPLLbYjARAgQCbExsE2peVi3FcKoLBxwCEort1Mt+eLzjHXND2MneljzHU5LzaEZAGYUhvVMjaI+Gjqzu4Lu5UdT3ZSWgroCtjkKTgsTGI3WKUn3FkHWJvk2vcITGUaJ9k6q/uBrrBrrNVXARNaT+VEUZ3qj5wquJ5bCMB43pQGyqBTgKCgo6tlShztPiPjXLJdxDV2kpXtruXn1NJb2/Dl+YS1sdDZ+2YWh1NHYTMSXpWiqKkLdr/Eo9IrgAs2z2Z5cmbaTMbVFPiyPU3gscCu86Y0fKteo6ZNtnK9b0az/uI/2WrpuJ0VL7c9Aq9LUfRqgORsxnFiljNLLb5ExeQyARLOyaWeI24DMgXAvm8XXHv12CSmL5sg59o1q5DFrNx6jcyYwbL6OHW4iqIB6Mxo4eaZM0i6W017Ga4EGe9i3iN1A/S5A1tHffL4lbSXsBRDe7eZpYQKh3OGlJcyuzIETsblUnvdT9kPHRuCpKJwgUOqonMJZrnB0h1t/lhdHkRf1kfldpfBA+MrHtzGLC7j85AFKb6F+6Yd9AD/8Zoy/n51r2PMRwr8/9j2jQUflnqKr0ZeGRXKBFI/ClxmDTfQ64Iw9as6sSDTFYFOx+TP1mPxgc8nBJ5+Ku619PV4IND39NmC6vO9jb111BTJWQzGrEgT+YfHRsP2l24ry/fQqHBLd81kHQHM5ClA8JD4v3AlpTmbLBkJ/AUHwAoU89xgwnvjmuuDpWDT6UQd2S5r9sYjq0BPb/VKf26b+QBwZPUkSJmow7XEX+SdIFkZW3OwYQGZJeq0nN2KsLEYGjBiUNZG0/z7tkfZdVJ4P2oRE9AruhSQQCvHBeTnfa098mNzLMS/z+t0KhWvBqyo0XNuMqfIuKa5crYFwPFeBcafMeJs+jRekVbqrgpyZBDE0LXFmJ+uBZt0nDACNMhwjZAEbQzCCNouRS0TdBlHFg/MpG+AAZlwh7kViM+YgTH709NLynF7d14ijXzlV8mA49FcxRxGXaaM7iX2nCll87WtxRUJVEXZOoq7bktSaLpxt6NTYfXxM0VEobvaftDu96epz2sfZOwPsXLSHhpW2uUikxXiwSHT4bymLnvPI7mSPo5rZgVq/T3vla7LhdxbL/1oe8/AQ+fnoJvqY9s3F3xsQN8kqhLah0jatY9lwXAzqEwkM/4RgHFs9xLytOJr0pzVBRxnIgBNntSExEPoc5KoFWNMdsglma/B55mQbb5WHgtaYlbrhLC/IwNGoON9TmCsnAbolAWGeFA8O8dFLNK7m5ZyOyvee+l0+uz30oHtxDsxjboHCdCggw/28uUtY1nw8yy+mUpkNRSvXcFr2ncASoeoFdSzXcbGWjfzqZal1g7Hi/5Olt4Wmn99jjlGUw79sknEUC/IhBHnWnSwonpMimW71Eg/BBBZB0VYmXbEQABDALDR/x/gA8NFwRomDCQ8+oYDg+V0vdZqFu/dNN4vzqdIAx2pvPcBVeSd6FrwpbOR/uXrW3Q1Km4K9OLAlICV5vqXpb4H282zZfgNmWwBBDCYgnYhMQ5W2r3g5dhQxLJeqgvGue+jeB1rl+T+ovaw0NH68nLa2H7m9Ph5HKiS76XhSc4AHy+wd+TLdjGODAC1nnhbbhEbErwqpLsXqxTbVbD7HJ29oKDiFMUbHFCYUO10ibrA6F0gVe14j3tR9eq1kCgcxzliMbtNGCBaotDgmk77ncv7AIinGuj48rjgL37xWVgv963h7ZPHi3iWYAYhAK1B9nej1dNT5aPWlspwLx8SJeYnLJv3Rvh7vynKxWgALhcyv3LtpFM32+C1eaS9Zz32TYEmKO9H0IMop9f2xch65L3THk4Sx4j/yMpIblTa2nKNvPcvrwYVKGG/+Hfam4J0LF2LrqRclHVthftkeuaQXXHzIR5yf/h8magtyz6tgG4fjz6+ueBDEj0uhYTv8boE/kg2qyXh8wg5T+dOX4zr81ROfnz3SCghAZAFCa7HAWmx5s+zYHvt5wOFIFhEczDtchDjHKZxAR6vTIHFbRBAADhbRdtaaDQUCgLcx2sILIAUCMFBy8c4zkaseG2ddVAj4LAgNlxz48yshxT2cwwP5tQ5nr4i8hXg5XlbtId87Uf2SUlcLOGi0WT58OuEeR5z4CT/zho7S9GTdyNbP/jz1jd8kbpSPcuCtN65PbIo8Nigbee4M2sGOqwUBD7J3892Z8nxv1UNJBaYS+Bx5suHN6qRHTFAhFkfJMak+BrM8Qxfdf0AbqUDvZi5XefvM/U8MCxUpDzfpaGVEuDjfdvxvl9wcyCwlYZNnUBMzZLQNZGLYViw+HteA0xTbU45zkqvdFMGTXmyiD3a70bg6nieHLvCYOf8ncUsdXQd6bykZLf4k5ES3VSAVqd7cfwqALSxtiQpaKHoKP+WEGqrRTGEIANACfr9GXP8Gd29rQnU9wwNKwvmnwASnrz7LlsJ4m8eppgLtqVjKI986xvX4fOuLcmW6OKyH01hBY+WNff3JAen6yzHReBpllsyxlqX+wQAQToe6Ry6ph507bX2jQUfAMbi88UW2mbVGDT6m2KwCFLKMhD8I3/OgfeXQf17ODihRh0nLAWE2AKh9vnYScYxuhmzIHwULCTpuaeXkLcncuWzbqPvk/BlzZl07B3yhgGOgd49iGu3BX87Nly2hlY6eump0JhVoSysYihAqe7jT/EapaTbi7pYlIjpABDaFEFNEcuiIR14awX9VoFb8Ywgj99J2oSKz0+aD/4x1ejRNCfcr/uYhxW45jU0xabwBVSEH7f5360VnK5Nrxo/AUWkNbqwJ2OndecegLTIpjDt/ldvb7CVhi/LE/bScClnKhTX0/30ruYGuUTI03GoxT4ww4EkU0gWj6tzaJyuWVNY5ViN7qYkBhpGGmk1y0MuIPio5fiO8dkQcnTz1EpSsYKttohn2JxyfHUVTuRamoRjscwR9p1su8b+2Z17w9ONXbi/P/cgAWM2CHk8rn0zK48Yq+spfbi0VD3eo0TWEueac5//Wbpvxe2sOI5qglRHrSO+K6fHxVRR7LVNY8vnXJ+FsSYR0yIzUBvrzvYFI7UrePt0w9EqrthQSw+AfWCAvuftBERTppe1KopTFFK7cfv04rFTEu9SVACn4ObJvnH2qEKt4YalAsR949o2tLOgkTX19IvlulR5TxcFJHEGJcBwRzgZi9JB8a5TOm1Urj2d58MtQuLA486q+kCW0MKRAVHI/BUQ8Hrcq2o6QTGIM7lH8lrck3vqm98v6uRs41LRH79/yEvKpzo68WF1Ym7fWPAhqpCeMj4yUOCDpsnk7+GiyEgxTfgECHgelg9fWyBJIMl6HJYXRpeJkDGR07UqXg/U+QoYScwAYMrsCQBCtE1AMYGeoXVIecAAWjTcIDmYDDBtjBH4QPK1uu81LuNaWtbsKVh4Lk3eBkCGViaiIQyYTbO+RZyHBMgDTExj7PPyUOblDcHX1wQO83HpGh9S2mkdon+dWmZFiuHAvXvkUQvztwdK0q0QMQRi5FS7NOy1xb0eNdJ059ob4z5mYt9UsAnC8lEhADqqGD/HViz74am6aV/mOjaarhdBlzLIrfg3f7alq2u69bqdfSguZG1xnwfj3FUifZUuPlWBOijOzLy5SvgAOi1+AnBG1DnuhS6WAgXTqhuM9ZMAkMc9stIQsJeiaB6zhKVkeS0aKbub9MlqAiCq4RJ4BNdMq1a4U60oH1N9M5PuGTT2fi2fvxUkZotHBphFFK33qAs0xYKs+yC1ZyAYnucsNo091SgXTPnZtoanbS79UIriJtXqTsKLUMaLC0y1tDzNdwy6DnDBzZTnrliEafkLoAmQkOWW77Ufslzk4yelqjzY23jOg2vlbfLBLaYPbGqTbEh9D+VsBTn5vr5nDt6lB8/2SvvGgg/ANUrXKlUHk1xkNeTG9dHT4ORBSvnNAQImBLzcG0nA5OxD/3KK3UzX4L3J9hZo1D+fKgum+96h4vRZvsYUh5LlsWDUaFE7MIK31JF4VG9NwOMUuz7BhwMP2Tq2veGyncH1QWBwuDmYm8m2r9TrfikZgphD2P1lFnHmStfcREyLOM96B1B4Let6SllL45rvXfo8FzlD5U57WDKKImYnRYwP0BvDOeKE+DPNpfVXg+eAjdnjXQvqV5R9J4hgdoxxYmzBJ/GMw7Rd6cZ4Ws4p7RPAXR2Rq1OpH1qWGI8aMSmowzpDSwESGNlEUOoQLrdbDUsH+x3z5vNYXfPOgrurAGW2nEzAA1w/411bSbRCO3+lTRYPCl+MzKvjrF7ifbwnpZRXrwcgrEhPXiyOgCqCanW4MwBEPM0tbbWRdfOgmOJKtV7EhGkDoK1Yhl4yb9ZidVp2Mpa6ZYp1lDj2W2kBYK9tw/tjx5NapeFLPbGVhm9tt2BZ7RYghyYjHZtAhndvqVYTs24ysNyk4SwFVTtIGjgreekdBkZGXhaAQJSjl06GawWq+v7U8GYfVKZ7NQ6Ud2XHeXbcsFuGje97GkoX60Jh9IEYJ+GNnPkSe3u3g8rpqcArqQyVsQXgUKZMyk0CLGFh4L7P2Db2jfKQVorLvHXFNSkDs+yZDkjPyvgQt9LcKeGKWWlbZKr487FfvzZIxoCgUld3BzxsRG+aQGtCbOo/78xb3NgyggO8Rou3B/tQIEH+8QheTjfCEFKKYRnQLFABJAvIa/N3JwhX4KTpuJ4EYka11S6ifHi6sS724FL9p7hbReyF5uZGkzBgG5/FZswDRVM5QQUwggl7q+FmsX8FLNpkWXc2YCa8YeRlXNQqw0+8jsuD8Z5S5PJYyP3QrR/ENYnsT4m1JtBpAxkaxGi9FxzkQXArQNlHDZKvahSYXWuyIFha46VYkbbP6g2fbVc8lwNPMszcrDlywCwTDDbk/D05IDndlXLzctGbc7rM/bB85CKKHR21ujYsgz1T/brq9+DgEbTS5P8omNUEpLnZCHDXKSnldYsH+5stFavLhc2yPcySJ5yb7rEBgAcvlziP7qdN+t2ckaeFmihjQR5VM2Zry+drgOa4tqTfZxCuTk3eu7kub6cHr5YtgBBgrqOI1XCQdqknNlrh6E5y19ieLGgtAjO8n8sLR+BxtBKGGI4z6bzpbmKNo0ipX1+8bM4nKKDyEUSR98JdqlmEShllDOiem+KO0rgNVCFmWQHQ9wf1s3reqP3jvC+o3AtkDkz+mc9daSIYK+bDzLGJGL042cVM6mPsNTrOW/f+lVBSgQgpmPqV52NVypDAEp//EXHbOUCRrEDsA+0bCz5UBFrE/HxlCJKpUStakKn9MY552LK2miZR0jl3wIRfLeazZKlbHmK+Hy0f8uC7WNzr/vwQafL69jIp+4ABaCZNQfwAsZcW4lV0u4AsgeWpebpaD1KgUoa5/FIHp8G1mcn4sjVLK33w2OQlABzIOKA5/WBaPaiVsK7SFBOrwxweqXnpJYtxfLTeCapiHGUGHivC/wAeYIGqKXYkn57XpgsLM+vb69W6YKvdQdwINrwswn5iNvVYkO4Ty829uhZr1W1v+HZ9iRoxwIj3MM3VrhnfYRQde+l7COpbq1NMAFv1XaxIc5eCpYOWYkKTNVpoaicAEVh/92oVZTN75900SQpO5BCmeW/puDgHOp2b20oGtgb9bklDJ9NuUPmfBb2OTCICj720YGWdUnkdgHQdQK7DADKBIjBARz4/A48c7JmfI2RZUki0jcq4FlM11kWuJEw3DMc+U6lfSsNZLYuFjLlPNVlyOkB6+jxP0TdXQE4PrhWxLBswgFcUh5i7iWBbfJ2sAR2Snm0oVg70yUmUlEt7WIsdqV41O1KIlzXEG5j1LAX7ibr7SqPWisV9Pd4E7iwxvudQKZ4MODpOGsqwztkpAFg09W4PW2QYrRikHwEWRYdjNoEnSxiYMlgYpBuZien4LL/4nFnG8R8DgnloH6zY5cTIgPnI9o0FH9IV5VSUY9Ds6qMBAUL4rqbxrPFnIDFZAvhxRpH8sQCZu4HlsQ8EWZi9cj8FIz1rucb88Ev/CTpIarN2ROO0sKQEHf2m5nLZzJVSNgcfnm+vKJCto27NNQkNq8RWOp63MwIayQMwNstFu1gfQ0ZEeveOKYZw4TErj4ou6EDEn0HU06HNjcQArxVohpUpbyZZO8AY36DsB89Jx/oxfRvkQ9M6IijNoESGMKYmT3BMLfDWhqil+2MGHqaJAoiic5t0r/1RrER9GYXfcmZKZiVlSmcppum+rVeQ34MVbrsWXOsW/v439ZiLinU4mVmPrAXLcNjDOkBOiPIBrZ8pn/NED0E2j9fIjlqFXlg2MNcL4fd0ZazZL1U0qugWX5eW9u1Cv1vxwmytY2bNqF3TQ9PfEuBroti0YIu5ULMmOSFbVPIVDbbUoh2bLFlMsBgMroUqG2pJxFnNFpjpHB1aBG2byb3e1DOsTSQVI516brSAPNcDb+oxWTe20rGh4yyMLzJCuSOBvu7jZnuvAGhT0GtYVppZALtaFkq4PQDQCjEsui6wU1ZLru6tOR5LgM3LGLzZjjlQN62JUjo4gNoFevDiQLakcm+lZQPIQEjv93j1gHeCxLxfp2MEGBphcnuzZEZYPjIASNeY9pu1ZfmTwEk8R1+OXauke79jv/T70TgUh/ieKA7QbG5sT1bAKOoVKKdCUzG/r2rfXPDRADltgi0FyzX5hOamQU//RBHZJvnYaeAzIPCPVsKVCdEC86S9glRnE8l9e9Tn9foBPHh/mrTIcMpZCyic7stLeRyH+VENeJip0pCMokAF6N2sIfs+LB8WBFpCW6e2uObwr4GGGVA8LhQ3tMxoEq+vmxfH5j8dU3QAhpwel+c0AQYAU+Dp3RxmkJhfXJ2HNXyirAbs182bFE240d14fnMpqDJTxamrtYIq/eqO2Ep3F9dIvyGbJ7oJAhJXsXjc4L4wfz9rt+Tg02A2hWml0IK35YazFK+wSw15AI8KI7/i+Sl6Zfzm2i61T1b2fa09cp/M/Rzfr+sggpQXwMHvssXjtXvl73K2lroQUn4nFhzcZQQJ0xoFIKwEluHjhGAJNDEGpIriktKqIT7nkFjEI9W2RBZKF4lA77AYJDCtKEC1CrH53aPF41LPu+DYPAabwABR9RouYTGTiGvZSpsym9a2xvZw3JjW+yhdeOxxmagc0/4d1yzqioGCVaNp8hSxYNu9tsTqKnhf9qlvtRr/CS1gepP5Pn7vyZqcP8esLFJeCBDcHfRgZ9k0yZrYT0ZWSQCuZd9Z3bcfarFPcY/KIQPpvrz25KLJsSRIAGO6QTqfmTwWIjYp5wSL5p7++P5/c8HHVCowTa7cD1o2R7mLGt012lFeGC40HOm6NWVNn7R7p58JjEwCXubvJP5Ll8rHrxO7AA8FFp9D+sdn39KzLPeLYx3ol9NNw1HuPsHbfJoj4tZKBPedZ0VrRuC01f1V3zTdM4z5mLg9gMh0qR653pUlnhNvAYOzUn+YVsgWsTlMsQ6IjuBtyY2mXM6JTpOUfs2aAa1Lj/fZea7desXAs7wHq5q216oHdYriqQ6XQ1ejIj+Lp4qWNsVErGmygPMtQB98N7fdN+ECK/Ve3fRf3Sry/TZIxRiISrp2puTm4NWCkabLqq12/sjyOEtDdyF89uI1Z/zc7Yx0TgpC3qtjUIHnoM218mkOSKUwzhkZ2e0yB5jOMRu7C+AOE7bmtig4z4J+OoeM//7l7RJppM/1wHM1GIDoSQAAYmRJREFU698GYJcTT8WsBQbmZKqH85wsDNEH6Xgqxyg4V4alqzlIGQuy+HicuBZLaRUuzAzMPO6h1h4Wyqd64lLOKc6DVpcMMDnWBDtM6z6ASSifvU5Ajy7Yo1XstaP3dhdsfPYSgFV9rd98P4nYsC4o1+IK1byvqNierQWDEJFuF68oTSUqLDwyAl2f6om2F1zPanPb3EV1uNWFm3pRUwC43sJ1qmMvrb4f8f4UwP79ChQmBccBTd4bIlHC9zMx3BrfA4iU1uzK1fW666vPPoWytVhqcj8Fd24bAF7wjvdN51POMVtSBD0HBsPAjypwvpGRUPER7RsLPl5tWbMFJgE9abPkBknaMlGqaJrkPMj8NQEGFazuz+nWsUBeQ43TwfPfXOtIfaBsjWN0Blv5+lPgERelC8BA812gy2qNQnBKVDci6K3MtaCfVlvjdlYc1YTfnX9dR72WnBbJvxkzYsIGKPkhNAUoTuOS4jxkJhLivK5tHQcgjduDoeOx05jkl3dCE5jmh6cKiH/uQYCmZ6vknoClpgIIK8YpiqKJERRlyoShgAAQ1o3cGorVWfHjqwOULkyNHHU+mhYPiiT4KKO+iBZE5VmxOA3WLakOiI6+OWU1cKKEG4OZKx3OZ+HAwPglBrACstXBVgOPzaA1XBBcBz6ePD/HUjxqU2yIxzzsbtFpxQQ9BTODTeEA3G4sOFqBSEU99+mapYwMG8bZUHhfZfPnbYuFcGQOBS0mzIrEQn+rsvihFGEALpAVUsY7VlP16TwGBMDVx+7J3aeQQQnPdUVq9uJofV1z5uZDWGOKW70yQGkpyFphPCTBoZKBjO9Nd4+4KJp0u8zH+LNni4tfaPO046HMuHu52Ts3pbJQZiRzBr9eXeOUGZNF49HGovPP2IeWOEEqRWGNiL48uBzPW629aZuaLLaC+V75evx8fT5aNQBAZuoFDk+k5TIGk028oJ+zkn9s+8aCDy2CvgOdheF0XhSRC06BfUoaID8nLe7CCWppAS0TpHkBAhbFmxHuKrCAB+ljo7/TOXmR5cN5L+/bdI9lcd0t+ryQBRFcqkusCS/C+gfFqz9K17Efwl7U1gab6O22xcZ/7iU0VJbJVmAqIEduDu0FdWuo9XSftb2BORBaiqVx5kJQgJvRlQja/YusBUGGUw5aevZpvFJKrQIA3TTLXGSAMo97CiLLcZK+KU4bENK6dE1OPYvn1iouAKSeBgzSCz3M8wVnB25qhdnenYOkCpjrauT6Jd/Zrngqh5E9eawBYzz4k0RWZDPNbolTBV+eT1HWnm4C7MATTjRx9k7vMgNUrfjYZjTrbcN7F9BM7zwS22XfBZfa8FyPSUCQVpztUhpuveL9MQqrsQQ7tWXWKglXiE82x4ktUl1hAjcsHlpw65ulmZ47rudmsTCk86/OKyMahdyKWCDl+3PHm+3Acz2MUMwFeLbYcFwicwiDTI7HjJRnO45CmwXlGLDa1YDql8cFL8dmBRwpgKtbPLYepH61jJiP1fUUY4IRFMzvdjgo9nVIsjP263Q+kluzAoC0BjW3SDG7pLWCL68XvFssn6xDw0w1VQStet8AaYkOIDWzMKiVUygy9j43+dfd+D14JsF7zsarpaO6W0qCQGTsH5H+esoAQlR2Eghhf4LTA68og8AMCLj3pD0nK6vIvwvuXCYDCMCEPfUgArMsvygTc2rtA/C0yp9QuNTi2tY+PXq2SGBIx9CKgwxgPqJ9Y8EHgLvBzR9nwBof3h9656dfBcfdvXgdTddeQcOjiXnl70CjuePrdRx5RsS16AyEVgDzqCVB+8hsxs5kSvRSDHisdTRis0jpsE0F4IacNp84HpiyB/LjFdHIWsibEzD6opB0PtI17K2jcCf613UOHszbo7WgCXhgneNHw5o+V+AOCOZ+3GlM6fkxur58ZrsJQcYpNsZkK+XnL+ceguNWLa2zaMUTzoj7YMxH5vcAHCxipl3PpdNPrTi143ABXdGBMmdfnL2E1eTaK25tw63XqcgY1wVg83o4bfcNFtBayqyVm0VgcEWYcMOI3/BYgQ+1lRNmcr0gjTEMhLHPTYd1rhezXzCls7WCs2gI29pLWEuuzVbyVTpayvMiF8sq+GO8McATQRD7dfPfb56GTkF/axVnqxEcDu+zFE9NrsPawTGwjBovrKYeNCv3NXuYyWQnjiyhw61yfKacutwxUmfDUuXVhxvj0fz9XStV38UBPbJoeF/M4OjM1TpetDBElh5ZPkBi0tW5oOPah+EOEePMSJXDhXuesBPpnDWW4pW9J+8hsWX7fvPath2iRdL+ki/NPUXuj49zHsk+mbv56NrTSQmfxX3T73H4o9cxH/c1iD6+Nvj4P//P/xN/5I/8EfzZP/tn8e7dO/xNf9PfhJ//+Z/HT/zET1jnVPFH/+gfxc/93M/hV3/1V/GTP/mT+FN/6k/ht/223/a17mP+dMwTmiwQ5QTQlkJhSMKeSE0S6OA10t8TsPDPJwvEgnIzeAnEty4MjHPp5uSaniwjatlpcXjzF66KBYv6ifwp6ZkAzNJsDEOseJPlfKgxLlYV01LzGIDKYFO25uym+97wfDnwvJ3jBVdLgSziWSDeWK+lSAvkzwqvx2kb/u22GbEYh7ybAAmLxyrc1U2mTSBngRwyp3RpGtsEziaQeT4AG0ta2GQpwbhGWM/U9mrt8MybdH2CRwAowOXpxNunG7779DJVE8002pfSUOpIj+0uxN83szadzj2xVsdlITcrw+7ulZ6CRKVb5dle8EV7Aqmyq2gQSMV8wUDO+5MVas3tc9QaFgNm0bxvRiv+3supvz93XNuGd8eOs/m5DhbIv3C2GiRYdD/V0vF2uwVAuDXLzDGh5qAWiPocsZwxu12YZcM1ubuF5bv7Szzv0a367tU19798fYvraQRbLbOa9hKWBePRsDkoothqw177DBaclj4XBiSwCUHoLp5rH1vsqQbivzie8NL2KALHNfFybjhbxQ/ePUWsgjILx62LcGtNrcPlEoR2WvDSNmxa8IwDl9LwVIyjhwGyuxeyI9V7c1cfgEGl73/fHGRyfTTnrrmd9pzHseE4qpU+ACbQUS7NA3rtJRECvE2BZu8RFG6BRQCLsEoCwCHT/sqUWAKesxdbf0kRujpgy9wisT/kRoF5jLBXFWAiCFtrR/HULEv8vHBbLPJA7UUbsmi9nswKU3zGc3jJLFxkOnTsefddHfflNdf9kX2t8/jTilEO8f7oyNYs6TgMuWVj8WFlIbevBT7+8l/+y/jJn/xJ/D1/z9+DP/tn/yx+42/8jfhf/pf/Bb/u1/26OOZf/Vf/Vfzr//q/jn/33/138eM//uP4l/6lfwm/9/f+XvxP/9P/hOfn54+/GSfzQ0DKwftXgq0siNLYrCjubtgEd5ptXE/SC/Pw5Pnz7N+bEGi+Qe6nptldDn2IYKcDl34JwkeaLR8MZFs/C4rkMqL3gZQSyE0bHx57TcdTk9XY9Ef/4m/FyDpIrJPhbqF1aAGld79nUPDKsdR0Jv/vV7U874+UNh/r4n5nAo9pDKgx+g2nIMw01oqRhmrnY2gnoeF2nF78iwXMquR5oiZuGjDdsV2HwMl9MwtIw3Vi6rT+Mz6ElWFNAJcAHgwobE1Q3b10O4HNTcHV+7TBiuJt0tz9U6dx4fOtmvJsMdG7nwRmBE2bc3M00tK3DddzcwFfRpXVtOZi7BVh5s5rmACtoOIkH4a318jjchotQdCLA6IMLLsKTq/lEm6W6Nt48aUotq1HoGldrEn5njY2fQTnonsKrKPoYvEdPSTT3F+zipUJeNDyEcXb/N8QuG6Z8fvfySIqQkWGVF1rutuFXL6NfZB6lDa3yKplV3EcB1hf5nK9tKiVlGDc3yr8ef/X9ras6Mjj40KQ+0/NzzodNI6Zj13AwHr83c0etNf2tKzg3c3PK9fWDz3oX1n7WuDjX/lX/hV873vfw8///M/HZz/+4z8++qGKn/3Zn8W/+C/+i/gH/oF/AADw7/17/x5+9Ed/FP/xf/wf4x/9R//Ru2ter1dcr6N09eeffw4AqLeOcgBlx9A8+5iYFRjE4g8Ya/8KAHS3lCAdk7IkeE6MczDr+U83u03jzyjlhFKn7qTJ5SJSJLDE7zyDI5CtpAs9WiCKhDKXfqa+TgG1ri3te0OtHtooipVxERibLUR9gymeLjpSYF9upm1YTMjoSG8pWBQNtcpDQcLnUBUnGRPglOk7NM/BjzRreMqxjHFZrBf0X9KP/EG2PQq6FFUe9wbml38FHOoWKreAWPwRrNR31WAKndINteB6bsH6yXREBiM+1wOowNvNypSz9Pu744Kz27nsXjaRl14DwDw5r8QuDU0KPtuujwXissMwbdr4Ry64yahySr4ICtdb33A0i8+4nRUvtz3AIwWlVSM2X3/rBTcvUf+0GwfF0eoEao9Wgw48XAtiFPwAAgwzc6R4EGl3ywjH71Is26PCxvQmFljLkvDsM2NJzsNdRoe7ivaOUhX75TSXhuiIWVoaGTyBkVYLsChdw9vtZtam0nDrG963HZ/fnvH+3PHl7YLjrIP114Uni8RtjEPx+KneBLLZ1vD2sxf8yJuXSKnNrh4CsE3MypQzXHYZFpAnman4v3++cQvNk6Vqn3vUfzm1uKWoTLVwjqOiHRX9qFaa/s2J7dImhSXKJvga5PaW9y3bax+j+RDYmrhAGtDebzgEwGcIbpGe7tGKA/xWbWyP4sqLmOVFjOcIVdA2MRfMyVRSuXOzZP2FciB/Ecdm0JAyLWOvF0QlXPHg18kSIhg05ysmm5Qm/4hW9RwfshwPDLwTlhcFipM7spAcsySZrRKWl8z+92hAYM+kVQYb+Ue2r3Eo8J/8J/8JfuInfgL/8D/8D+M3/abfhN/1u34Xfu7nfi6+/9/+t/8Nv/zLv4zf83t+T3z23e9+F3/H3/F34M//+T//8Jp/4k/8CXz3u9+Nf9/73vesY8cDe1fWZB+hVSAWQD5n/D4jFk3AYdpe1mt8TCPC/tC56x7GYxOpDnOmKVWn512F7Qf6kv2Zj17szI+Q/7HIFmM+tDOQ0BgNz1YnrXEaz8UaElwXia9A8mauGIGk/N1/ymmARE5jF12Bx/REeYzSv/ha5n9jYB9cY21+sVfPA2agknzRKwcFP8scKVHSXucy55s0XEoLnpW5uN8AEJNP3v/l4FJaOSJrxoNT2dbsEZ6T+xSxIe5WoMDLvC13/C1AuGEiJsR/P5MGfXA9LSA1E43lz5m5wd/zv5UavqUxzzEhbHmt5nvW2kflWBmWhYhFwSjeFoGwkMn6UR0ssU95LcT9c/9SH+z+bnn0qrO0Tm6l48nTaglACMxo4XhEY79aR0YWzogZib5irLEW7/4859ZZWKo8g2Brj76PNSCDwp5rJJS+VKl8VQJikB4QY/nk5ayy1QqW18+Y4LQx+Lsa1WfXDA6/B/eajxIJSY5Me07J+85yMe5l6zOm/ewOeCx7HR79y9fs87XutrC1L9N39xvqQxn0IZn8Svtalo//9X/9X/Gn/tSfwk/91E/hX/gX/gX8wi/8Av6Zf+afweVywR/8g38Qv/zLvwwA+NEf/dHpvB/90R+N79b20z/90/ipn/qp+Pvzzz/H9773PdT3h00aGSgFQwBjLNjVihVo0I8Pi0gBwGJrWdDXhKx57TzZ+eIyXXIsij4QIoUQFxT5RCZrBsZncQtqz0XvqgTGuxzauo5zuLiyho4hrPvN2A16q2iJLbE110zPe2jb3c9sgW2wkt7ULNwiYloNEPRaC8CpVXHZTjzvZ/j8I9X0rDjUrSYseR03d8DhPADTy7mOO8fnlPvv86YWPAH2c2guOpELiaaxZeBvyRdlf8aamd5Dz8DKpvAsrPKxHWLl2b0zm1tDSGNPwfBUh5ZKYXc0c38UaMQjXLHhrHUqDPZlu0RsAim0o7AbjO/i1BHwmYNgCUjIGMqMjKPXmMcYGQJVCgPVFDQsEI8B6t25JIApyJQa/yyELYboTOsjhCW8SmuBWYxS21NcCyu48n6X7UQtIzW0iFkv1F0BUhUlaLt7osQfrrOjW4zKXgYNO7NTOG6b9GAN3ZyhNtxCteFZJejQbf6tz0/b6HvrRs9/nsW+FevbVm1NbAk47JqI1TDPJQNIezEtp/iLcPQt0qgJWNl38qHY85awbgWVex3gRryoJEEH906ymbZmqcz9LEPRyCm2m8Y+Xw4MFmcMjZ7veSgPm4Gd1gfg5jOzzlARz6ryvjbe/y5t19/5ze6tDvSitH3aL0IeMD5ixOvOvyTlkYrlncBe9rDQxzwzbyqCyS6Hy9nlgCRklEFHesR8fP5MqSgtz8asm/ibcm0dNh3PVU5BOYB6VejLI2TyuH0t8NF7x0/8xE/gj//xPw4A+F2/63fhf/wf/0f8W//Wv4U/+Af/4Ne5VLSnpyc8PT3df7FCzSTjPqT9rwt2ut4jxOeSTSGx6AKwPBJ8+dzl93wLdQDywOjw+rV4b/mI877q+wSM0My90UtB9w0k/N3pcvklipgLDLr1lURsLnmNSXC82q3QlP2EVx70DqXr8t3y2cO/87h+6J2Il3ntwINrcWPqM9W6mZPV3HmLxkyNNPaQRdMfGRIFZ2emxvgOQFxv1eiypss4Cr9LCOjQiDGO/RBXRvfF21M8xuFWD1oqGOsR8RGT1YLgwe5FF8bmgv0SgbaWaXKTGiAkP+9U1TZZN4KMTcs8xovgzYX4upcUbqK4lTr191GL8V7mjMCr1zmr5fB05Vo6au+RZZL7sUnDXkqcS2BHN0Hm0TFXlDGwTp5YWl9SnAbb+vyrJYj8LYBxwFh67RZZUXGdYJtCzBuAQXgG4JQagp0WmVo0rFsGNh3A9wLtrqakGk2rW3UOsFsnJP3qMSWrZSPeK1iMVNdknY39Jp3g96er5U54LzLj7n1fj9d0jloV9jsZ8mgfe/D9ujwDFMGVn/W8V+RbHE8FO918uofGKdY65nGYT106N9/zY9vXAh+/+Tf/ZvzO3/k7p89+x+/4HfgP/8P/EADwYz/2YwCAX/mVX8Fv/s2/OY75lV/5Ffytf+vf+nVuhb4n7WqZ5OGaQBpgjEwVYASDZY4OotxHAyRebA3z4Gr+e10Y+Z2lsMz9em0iUr9zXxQUYhhVCRPCnCwe6Z65b2H9YByKaxL9VgaZkcPWrh4sBjh7qAMD11C0i1liihEhlVxnQmEETfn23lGarMlQ2URtM21lmGFzBP86NvnPlFqbTYyiMyqfXvAyxooWrTHA4/f1ZYxnyRtdH39PUd5J24jsqAKIa8uXKOZlIODWawTGXc/NN0iJ2JDDi3QxW2JtRRTwrBkGsVqBuduUycDWVaJCKQX6nsDJidndERlH3phBcG2bxfcwDdSDNY9jc3P6sHiI97MwU6o2bNXARlS4FXMbhAVGBS9tx/tzxxfXJzDVtqigiVjw5fIiEYTkYmm0QowCe8bOetYDW2l4G9konmZ7KK7YY72LawqrG4ZjyTTiI6x+i+Dzd2Gr3V1LFSjA5jVPnpzu/LmeeGlbxPTYtT1rKbGPHn0893na9xZDI17YsU21cu4ZcHsCIz3m/9v1JY75QX/GF+0pXGpFnBdFtnDlbFvH07fPIIOzfox0YM4pg6v5TC+eIXP1AN93LxeLIXMgIEe5j+VKsXXT/rlwXkg1jpO9zm4tdUvN2cw6d57V4j5OGfxAsX/4/Rjr0YYCEvssN5ZH+zj3DxnbDjD2G9s3xF06GqDr7tX2a0/7DPd/3irLO00y6TX9IWRd6msbfViV+rzHjs94rN71Z7pVmiutVgj2Y9vXAh8/+ZM/iV/8xV+cPvuf/+f/GX/j3/g3ArDg0x/7sR/Dn/tzfy7Axueff47/9r/9b/FP/pP/5Ne5lTGmLSADwFiUryyKO8vI6wpeQsNZ2rgVJAv1D4GIFRilfoVAfNAHTb/I3YfpmgKg4yFKvUOcSx/Un4ff5+wWhVGdj374y8HxLaZhEEyED1r0nk7dzzeUz8yWYVaetVnXaItCHwWEJndT3ohoceDLovn5ZViuxhgl1SQDhvx3XD9NwjqfeYizNpDHfZkHC1S0+hoA0NXM2KyDQkFGYEYBumrbwOzDZvqnFQyzNMqnck6gYg0+LH7vBkurbMphnqu0khuE6bps1HbpXqjFS6T7vQwcYBLIj+Il+CwiGhYapiBvmkEE0EHgKJPAYyMYmDJFHGQdnv2TeZ7pfjk986V5WvCa5WJzMH5XtZRyBQI8MxXYspnG82WW8K4SKbY3UXfVLLwqPv+5PQoOFu8TwX4mcsvWktkSYunRBwz8dOXcFzQIKuY5sZ99+myThpvYffYIjh5kZk5ZPM1v7v9em7lodSYXnB+MmtUQuBNpY+xd88soBcjsycNdOPqT45GmjIJ47y3jJbs0IHydZewJ/n6zq9H33B+kZbSuJ+Uzeb8mxTHtuVRs1r0p3y/dV1PXox/p3hNA4b2SfOC1Jb7TezdybqsczPvzX2H7WuDjD//hP4y/6+/6u/DH//gfxz/yj/wj+O/+u/8Of/pP/2n86T/9pwEAIoJ/9p/9Z/HH/tgfw2/7bb8tUm1/y2/5LfgH/8F/8Gt1TPcSvkB1TTYHJekyUdaB8d2jfOpHx2aGvUf8DcinLZYOydf1fczYRTVQ9sSoCkyWUgHuU0cV4SfkYgwQw/NSnELEJfDZU045Hvyj9cIqOhu/xNqkKLBZ5L+IYmOWDMHGQuuqaQy7+3R7mVMPLR1Ukg+2erE4G6uo8eBaSLxIxR895ahzDNY5ztHfHNsY7wegIa67nHvX9MGYLwCYIEaK1TSxmiCjciytGu91N9dFt9RKxSy4qclReF+25hrpDAi+vV3xne09vlVHphjp06dsBnHG0w5c+x7HHi6IWd/jem7GyFqbxznYzycZ9WKAQXp2bZb18u42CnlZIHIZNVjKoOTvOlg2mZGxlWYaN2YAVgM3dg5/XMMqzY5+50Db99jxZXuKirMx7kxvPS3V9XaaZhwuRGos2fpFq5Cnbt7OLWKdAOB5P62eymbjw4yd62nMpe/OHbdicSAc65dzx0vbDIwk4BEWlsRbsgITqFkMz9MyjZoK9tLxhDOqAUcROC249YpNBN0rc47YIwsqqNBwwxxl7s+lMA3aLFNhwYsaPhU3IAjgOjwzzZsBAqPpb72glRLPwDVphRolPpZcnJHVV2NP8z3CDyi1YdtaWA2DvVUkMqkieJ6pwBT0vGdVKDTcPmHswLgv99EobsrHyFsmFaK0F/DcARbEg1u5P2uwuILu722cFv3AfE0FRixjHs5QytJ42sZi45YzH/PeBdtroQirP0GIxHikWLgVgCzt6wKRrwU+/va//W/Hf/Qf/Uf46Z/+afzMz/wMfvzHfxw/+7M/iz/wB/5AHPPP//P/PL788kv8E//EP4Ff/dVfxd/9d//d+M/+s//s63F8AFBJJrkTAHyDZqApMCm20Tg5LqxCqOj4blJ4kuAXyKheOu9FyIfn32U6H3D2rRlMrNdJ116tNETKgSr1tWvcz/QHJ18RjKVZkwrgQJdKAk6ZNEhk+Fm1KHp3kNL9yRWhSdIUn9t9ds3c4TB1co58DMO0+QCE8SULwb9ck89998IQTLh15M5ahnTOK6rApCUsayVnjGS3wFZ6uB9O8jwEi6wJOlqnmBYNIOizc0bHqcY4eiy5cKGJL7wNOTYkc3ycOgTm2kYsynz9/C82eh3ZUr3X0HqPs0asRxFF1aFFb9Jwag268+7zVwQRO8CpyGNaqwEKxqFEgTS/Z4FZlJiB8u684Ae3JyM0Y9yKB1zHFKa1w+eqxYQnfBy0qHFbKIz2vBVPT0a4YxjHcesbuqZA4fSc5MtYxzYDtbNVfPlysYBTBnyrs6967RkAEKnYIJG6zQE7ewEK6wgZw+xL36Nmz15Oq+2SANy1V++3DJdJsojtpYXLhUHPtVhuDNf12m5uMbJ+qVs8OavjB/e6dT9c3111BYrBu3kNwvthQjrtJ3lfSy4cFhnN/QAP9T1N8ECh875NKa6KaR8Z8XAY1uRlL1EZ+2sos4vsie4lWUCFNivgedxiCxdA4OEEC+iYL56ul/qWrxXf52dY901JIOYj2tdmOP19v+/34ff9vt/36vcigp/5mZ/Bz/zMz3zdS99fqxvqLKdPpoiZZEMgvnZimhiiVVoY8uc9TThc2PYh9MKXL+OaRLjTmGdwIOmcEHLju5isNTebC8gFIj+bFtciIMZLMsYkPY79zs9dC+huMldg1ExZJW/cyz4n8AiTZjE1QNUKTQXwCBrohL2U6bdZOGVwNsBPvn3fNIJl1bNI1DWiyZKU5nhwuC+Pkx+RL3D0QYYFC5iKEb4GQEMLy9paOq4xHdU3dqstYqXSq9QAEK0VNC/g1291pBwXhb49re7IBehdcUpBdauKET5VvG+XyeUSxc7SOmEwYTZPc/FRyFCA5jgGI0IbLXODZEBVi+JsnkrrvDDqWQjmfgEul8GOS4FOk3nrJVgpT497URcmGRAx5ZfcJrQmUFhyfKP2i3pmTq/4we0J33//HCysx1Ena914ZgJut9qIArHWTajR+nG97riJ4iVRssdr++SxMs7DcTSLN3nxCq9nyyRug28ngGUvOM+K67vd4qJuxd6PzTLNstslflZA1YjqaAXoahamVhqKZysxFujJgceoVLzhpe1B9d7VsrGOXvDuerEYmv0MkHk7qwHLzWJPLlubwAd3D7Kh8jPLsJAUU5AEXd4rgVnacfMWI1nbqnGZrLE34lbCHJytcS5ibxuC3scw7jlux31mSpX1fpp88HOdz2Pl7Aj51DHQQ/E9O+03Zvkd9xdFyIfsTaM8KodXoN1mkPAISNn+qNM4576uitej/S5kj8wHzC4yjMzCj2zf2NouuskEIl7T6qfxzgJG7r/P2vPdZPPPdMwdSpS7X+3v7BLIXwiCNGY2fWGatFgIwNSZyQKTVkmMBV+U7gCE7peUAlZOs+bgEIs3AEaktooJPLH4i6h22wpwejBh7TirFwvzjfZ22yyN7nTG0pxGx65dBrcD3QzZtEvaaDlc4NY0cHy5aX5l6es+D+9s2sQABXGTB8AqfZXBIC0vA6yNPozjdZqDuzWp9kzXVrG3LUzCdrlRcj5SPUsfbjofk5hTF8DnWdFkpr8vol6AzqjUCzSCS5siarjkLIauEp93zNYSEQ12zbyMiyieL0eYt3mdpoKrU5DT1cLy5a2VMHP3UkzTVUu95ntzbjkwFkGyxUyFihHw2s6K3ganxlrzJrhNHIi8b0aQdSnU5Gu4RMjCysJ/3YMecZqk0GqZGQRHpwzgVotJhANAbwXnl7vx0FAAbQpsHfu3nCTOSchUxWnKRwCpwlwW794/WR+udd5U+N4fBX5bI7C7KHotOLeRHn3ZbP64zpqaUkDq/q3MsUEZrOa1MVnD+igil+O22m247ZoHj99uRvh1PfpUu4dg8/Q10f14PcvYJzKuSH9PLb/DMu59NgP3VsnZqmbTQtUc5NbacTgIUL9+BLbesknc9umMzbM8EST9Lis+mWRwbQQsOnCH1ZTRad8JZTfdTwVTgKcpmfwDg36C3X8VMIxxzYozP5sUOU5JHKPjWVeTyGqW4fU6cqjVV7ZvLPjoHnD6IeARLQNkCnLGCsiDYxKytIPHIcEJkXfhR4GGPO8rQBEFZFxvcX/ys+ADyS3HGeRfeQ2fcCGyVnshBAjXlO10gnIrtoHxGvGi+apkKpzA2EWbWHrcBrS9uDC0k86jmi/1VuP66EC5WpwOqqKfJbJdAESgXrhjHPiUm5jFZE+VZFPQKZn3ciAq54caSYC0nr7D+PzhnlYYYOUCIcXNGDiVsH6pwCSi30zzmuIY+3xpK7gemwlszBkCJG3iGFgcDaIeSubL4PyyYjAAlDIyLd6dF2yl41oPPJUTkOFiqeIxNt6v7HpZgxrpynlpBbdjw3nU8OWLANenLai8AQTYOI5hLWHxwX6WIVzcR05fce8az2luAwxLgZLV1P5uwLhmE/Sj4mglrB3oCCCS66Oc3WId+Iw3VmQNOvAS19UOgBkXzQF6Z5qmuT0ARNyKBd5K9Lf8oGJ7J6gv9tnxLUV7U4DPLM6n9QIVjRoqjDEp4muhF/Qf7KjvCrYvxWMAuDbTT7FYgb4LGjp0K2h7tbHy3Ztzw2DwDsGOBlbV3ZfA5CqzhGDgcU9r9EwSlRbL1sq0nmnhimwhGcHpcW2SkzG77bT3/eFLCUyfh4ybND2rvM2A4wIJUK4eXB2Wq9rnWBLuE01Qr3BBbtweumkoZBkI8Lyo2pr75NXDp/0gyQ0tGAGnvHeyelAOCTDLI+CuDksOdteqYaV/zeIBzIrTpGSVpNCu8yDjmdh3q7P2AUGXQI78f1lY7q9piwGDB57qrO1ioNI7qu3lGjw4z5PmayUgcYcm5f5fjodQDHQbpywLIgRrmz4eF1gXUD5AxuTHYgbuNqv4Pi9U9pmAi6sqzkmd1uVfB3CaUGkAerG0m6ArPmWqEFlunqG0A9rGZlVcoyXjZXfTPE2aAoWcgKhMplfJY7805WaA9JKlSPLJxPjgBbvjFVjHIN+HY+2LZqwdXY6xehF0ZRTZJ4F/l64J+GYNZBN6FspMs4SKW29NGH5rv+Kz7YY39bjTZmkByZlG/JxabnEKbqPhHoyeCoxaHaI4HURqHYDIQMEinJrMwEP9JVF/Ng/+NQDi4+VdI9hRR78i6mmSDtTohnHrB4qVe48KtZ5BdEiNDJDnegQVfNTHSYAmCKcCuAr0ZuN2LRtqHQXrOIfhNmyC4gCdG3V/UujFUkBHlseYd7MgcH59jouib7a3SXeSLX+newXObym0mgtSNwQTJ7huxKAzeVlAgSyKSzknwHg4Z0uk50qPDKeD7iwHzNXr1hwBNO7X5x1jKd+B9EoRZGnHIBlbODVyWitdDMGPsbjG+M6VolNgdljlXOuYgnWTsiMqntZ7v3fmVNsIcgcSaMh9SJ2agNH82SoDpmvlPS6BiykbJl8jX3/dz5bHnWgGMH8HILn8E71ECksIy0sCWrLcdN1fY0x/LVg+gITWMv3tOtljn4y/Qxjgfp4md0wyjQUgzcKXx8s82Hcab/6cCyz3PX23FBadUekKPNYHCDiK+QQHJ9TkxdX9O9nKh1UYr0fcIwkMIOXcCxRqWksVKJktmwBnsRe2w3Llm9GgawVatWMimFLGhsuCUDTBEOGXY1gagDTXy3xP/smM/AXo/kyKhOwxvl/H9G7cV9C5tvRimaYnI6grAJ5tuK0b5wCAOSDThTdbbKIlZxNJCKzzLLbRAyiOSqoYX8Qbt3qwlgmZKoEBPBoKKrpr4E6Q5YOxe/0PCwblGEisE4UFwTaaMTgMS0Cxdgzg0dZFh4gr0l6QyzjnQMGZuE4iOJpaJ8fw1Iqio9YMSc+YttxUcPFaHy1cM8uzMTYpz7nC6wuZZQGaU4x7Ag/2PNysVWzN667ApqH152DdDDymVu0crQI9HXwwzuzJwVoF+kV9rxqLUwRTjMWaWcaMIjbyjjD1+r4Aoc3vVppZPZI1JbcJePTxTBI2RB7n7zuBXgA+31+yEqQ+EbQsYWxL03tsN5rSbAEEI2tOBV6Ly425lsmdKt3H1oW/AHPWY1aIXgMd6aNptLIwn/qQDn4kb/L+9AB85CnJSlA0JlvkDqU9bjo8bYJmTfZdP1v75cPb4tS/jzrQ2jcWfGTzzeTzQkKtgnlhcCNAGrdX0GKYlPiVIKwZd+mZ6fr5/o87jtmatQi9XDiIbdqT8mKZAphGVsYqdIl2Ff5dTyBjG+92PLgHcHIj5ksG+D19g6BbR28mTONZzjK0FwH0Yi6ZiNPxeg+rBY6MlbnVa65B8zroyGMVX4kJSOQgUWBYNbKLJK0Dbmh8cSdt5tGLL+PftJFgXAtqIEw3s/icZcRVZAG78p7kY6aYGKXwHTwqoNYMREAlYwvo82dcx17U4kHUM0vQA4Tc+mbl3tsWKahWTdWDJkVRdrOG1DqzqgZwcskbpHRpExWvyaO7erG9ZsPn11urJQchXXM2z9Bq3SriZnZaE1hj5ujVMnX6SLHcSkffJdJC1zax64qSWCQdMOadQIJp0Uy9hSj6rmgd6Lui74B894Ztb9i3hq22KWBXRPG8n7HEttrRdvvrPDacuEAu9nKwlpEKUF/MSqTXgr4D7dlcMM3jPvZqayFXx41Yi15Qqmf8OPCYMKR3rsGsYJYJVRMgSWCmKETM7aQq6NINHKKYu9atQQYSLXjiThDL/E8I4g4EmFuVvImtmtdQWxPMWuosIofBQHtr1anpqwlRHeuT2rmc9nu5Dmttr25h6nKX2r8uJUlrJWeslGVfxoM9b3pXeI81qDWDkrvP5wtO1pJ83wfAJb5fgIxWgLV2xgPO572mbCuf8QEg+1D7xoKPV1saDPrM+HcIfQKJfDwPe4RA1ybLzw/0Yf08BNkr54bwXO/9CmJ8ZDorjG1wU/adxSQE4gzgiEfuLzp+RvoZYy3EtcRssaH2EoDPLhBVHFNfgv3yoU/Mr9WWZ5AHQ5zHa0Hua7zGh/yT68t7Z03DA+CRT5EHJHTsdgJttHQAA3wwoJKxD3E/0YiJuVtSrzwLN9sWatuSheLcDpASgCQE0HoNWmYCWJhZf9t6AIXsDnrY0phJc/BRjc8gtGMHFmERSM//Kt05LRVpDHM12dYlYjq4xrYUiMpG68nU+CIu0oHHrVVn6R6CALpZunl/o9Ct4+n5tMyP2sKKFLE9pWNPZG0Miuy94FY73j1XaDFmztIUenMlwgWkelB47w6eEt/ICLhNz6okkMuWkZEF1CFor1FWPmgZDNq4eBic6rB3KOz37uP5yruax1poNeU+/siyPXVkjCsBlnVovG/N10Skr+vo351ioUC9meBtAAoErToPUl/uy395b1gVGv7eEa6LOwDGPqwxHh8S3L4xPAIeNqZLf2Q67dVxHP2XhyENd+0RAHl0zEe2byz4yCZx/ssPFn+vSC0dp4qJpnxCk7xO+iUu78JPloWSUSFBTlyEqLqkcx+hzYIpRenOtJavKbjXBBKKX8dkup8HFhFEKFNqw9xMkJFvgEH+w3GjQBW4tcT/LorLb3jB5XLiW8/XSJu8nRXvr5eg3uYjvbZm+8XcOmsszJ3FKoMS9i1fOGlJDN4NEyJ8M88AitdbNpBcOTcfN+ZAxnoEIkVYBZBDIMUCSd9cDrzdLfiQmRo3L+JX5b5Gy9N+PsxC2GqPNFbyG5BafCstXC5FdIAMwNksvVS7MxhlqnXGBVyKFU7bisUr1M02321rkxvozooFIAjiigKXbkKyi3lZdgMfDKlngGJDCUAz/jFocMQEdd5TFKiIdG9zJzScYjEKwe/gpFNP+wkRDe4SUm33Lh6PMXbmfhj5mnaNdzO0OX9uEQui3MX847V29F7wstnzVi9G93w5LP1zO6OfBBub9KnsO60TAuD54kG4Z8Xt2xtOBnI7gCPpnlbLdpE3Jy5vDuz7nGa6Vvrl+mkqwWramwDVjnnCmVx0rHzsYylGMHj0FkL9VXCYW0bPBCyBjZfNzPeeTMJoSgpm6yf3Vfh+3gTH1YpS3i7OwOqZPT2efxS/681B1+nAf3cA9FZN6dnEwIe7tnrFJCdsnS/veyhUiH0j78WxfeTPlv0+lNDVip6t+uvwCh6DjZ72LgCdmncCS2HtzeVFHm3M+Xik58rnhPKp45n8u49ZJmzfWPDx0S1N+MPv8guxoN/XBKKuf2RBmAf3FakaaPO1GzzSCj503Nf5TsbK1nQfLvoAEoxgzkL2q/qzgKS3zzd8+/mKv+7NFwBsE/vyvOAvieJ2brhet8HnkDWz1Ffd+DJIBMvG99x4VrD3Sr/4gk1zqwZAJL1QUNyxFGb3ycNxiB0mbzaLuwfW31LU2EGrCcKjV+DccLi2WRkQloTHXttdIbAcJ3JINaxdSNjVB8PjAjzWluNAAEQdkCo0ubsPnRkC7r6wc32IJiuCAyeV2Iwt7kVdK+9QCzAI8rqwbijdcTMde+/FUo8Zf7CsTQEmNsutdBzu2BfAM1I04j0AOIV9BhHkfLCxkOZ9Wt9p76+l2Ho8jL9ARQE4dXjvEkXzdue5qNN5I4Bzk+7cG4Lda9pg8zl5Bs5W8b529C44dk9jvlkcjR6eulbNHXa5nAFg+SzbKzEaDC6OtbBIhxEjMT7PRftWQDyuL9OPu98xBLeEW3TeQKd38rV2J4FhMWjJRVmS5ijexyrqdak6RKuvRQMa3aW/0NVQgb5bh5QK26PYpdBG+VPYpfs+r4LYQYO6xVjcijVVX89A5muMyaSUIsm29bi8L+b9Pk9C7JHyEZOTDsUDZfgr2jcWfGhGwOkzYP4M8zqYg4uQBnuJJVB+ttxzvS5kEVSrIMzXq+PcQOtr+WWCAJ6fIr8ntLr0R0Jg3sdSTH1TxAbLc2wsfQM43QJQU8cVw+/KF2FC7RrXBwDdO7ArvvvmBT/y9B6/8fkLVBey5foW3y/PuGymyW+1Ya89Mjx0FzRPK+1NLCaAmTNNUK5iWh+jrydggXhxM935aiUZaN2fuSBOZkAfXVaiGGltrt3eWaPimuntVUnXxrDQVaPe/tZ+w3ef3gMAbm3DUz0BPN8ZuZ62E3tpVnzNSbKA4RJ5f+5OKjYAxKXcAxUCjAxCKnoEFrZESd508DoUsaJnl23D0dpgH3UQUlx4n2LzV5zY6dGrQh6N46jop8UcgAJM1DMfCo4Dbl0xoHbZTsDdFdfTqLvPY4sCh1DBVhvebAfebjdspWHrVjjtB7tVxH7eTjzVE999eh9xIT84nvDl7YKL84owQNPYSSu+aM9QLUHCJHtH2Tuenm942k985/k6gAMkiv5l/hYWyQOMe+SL21PME8Hj7hDuUhou9ZwsE10FL5vN8e3Ji/d59s712AzEvwx+jTdvr/j283UUJPRj4X3bvb+nFhTtkW77VM+p+BzZcc9ecSRCPDYWpiPQAwaAbA7mTsDiQEqKS4rzbc73zc8pFnyqnZk+gr6nGIP8Hue2flaAsnXslxOfXW54qifebrelUJ+gFStOSOArl+7BvRZM2QkueH8Wf6Mr6DSOpDkeyJWPbAm/K8khM0aJfesRmHnwvFgAyPKiUUHLCuyU7edgKsYuKVbcF6dry3xs7sSrIMjlCeNUGPBr9PEfjz6+seAj2sc+Sxbg6w6fDpmqBb52/Lrg8wS9dl9e348ncHyEQAkSJP39ah/89wmIrH1YIpMf9e2RBpF/H5aRBfQ9Gv+CUb21nsYz4Z/nAmEEHqw9cbZhxh5mdl/k3TNrSKueQVlSmB4Bg7uWX7IAUOPzoDsG7l8w8ZiOR+OERSF4NK+JFyKyDeo56m7kYRQN4MHUyK49cS6UMIGvwZMMwMxttX7QvF98xzoXcrGp67R+yHCH1GD3BFSHmjqOtXOZWSAAetGIjShidNoR36LqVgikOAINS5CljtbgANFWRjVSP7aIYpeO7kGSvM5eW9TU6VrQS8OtV1zL2OLoComA3wLTygk+qq3Ly9Zw2cxyRQsGU3yr1zhhvZNnBxOnWnq1yOVVFwXrowTxnFtCLtrQS7fKowBIYc65IHuqqlVBzvEjJGN7JLkzcRiBx1dZybqWqDYcY156WI8AQHwOaUkKfhogpU3LNMcQFrTEtLeM8heP02uRj+efBWGdCzCoyQroazOvZRbJZLZSXHMb65pZfBaQ/wELRLYYcK/n59w/0t7F76YZkuV3TT/xcDo/qn2M2+NjrCsfY32ZLB2Lwvox7RsLPsrJDSsJxnXQOFn5u9eEpk+uB6vPn+ffV1CAcc/oR7pv/CsJPAqM7jh3Nb3v+QV8VPhsJctan0VTX6BAaSlzI/mt755PYOl9K9oVmH9+6TMcMTOlVp1UB3uHVI16EgE4SELWCrba8VmKYyDJUvj46ZNlmLTYwOruiNrfaGH/8hiQVriPTSs0AMnaVPoHe0Zd559AJc9D2giLB8OKSGgDYQVJIFMUaLv55YE51XLD0CKBsXHuwbORSt17HRBeg+4NBqs2L+r2+e0N+l7wVCzl9rkcZuJ3/gYAkVKJDg8wPFK2i2XL5DiE6oKGxFpFFNX96d96ahHXk830wYEB4CiK46zQvXkV5A4yswoAdQWeIIBVYe9cBV3QbxXyvqK82Po7f6zGmG2l4dBidTx8jKgB/8j+Pq7Dz744nnBtttXl+IVtP9GkGsmvKOrWse0Nz5djKhpXoBE/RQvVpVqNlCevXIyOkXnhIKH4eD7VE5dy4rmadYagsTsTIMdwtXyRx4O1aM5zrIuaQBTL2edxNIvFKL7Gz4JoLAUh79JxgmnFYx5q6dggYKXhnCK+14bLdsbzHsyWOjZzvRUFilu/YNq6thLWhXUzV0EqeYB7pZG/AEFkRpr5lzYsQ3tpKPuopsvYD8572WzNqNhGULYUlOsBeTEEefOVsW/q0jlaFh4Bhug3T2cQ6qP9GWM/WfdtFYyqv8sN+jZkJa8BvxdZR4OnY5VxvEzskUs/UiZiWFBy3Ijvk+RP+RocY99c8DE2+fR7br5Op8I88xzEcfkDeWXSvwZgu9e8V0D06GIPJiVeqnzO10G86ZnvLvpVD7SeV5bv3I8omhZU2hherasDTMILGBorBenDzJdlIwrAtyJspN8ljSEwCIsetXSNu/Xx6FjAwYbc33sFL8uGOQuBjp7AROYm2ApTHBHfn04GRcGiKndWD2C4ZRgo2LSgrCQyGAXm8j0ON7W/tM1YQBNR15oDQXB5KX7tAgtI7vfX5bNTW6aFI8cnAJZqyriIR9e4axQ6MtwdK8kUv8uEa9dyYit7xIf0B2tv+luG9SeeH3kuR8xJ/pn7n+cNMgD6lt4HO/Zxtsko/jeq/Qoev2987lfH7SNaDljOz5Gfl6nDUXhazbI5igqmbJPqG4ZrTswa0cyt4k25j/itQ+hm5Y6fY3zONPTTafCf6jweGlaQdK/pxn65ZV+xvSbtKFQy7vqs4/uv2K+nPf6r9va8nz+STx+SO+n7kIP5+ZOS9OrtZf453eorzsty+GPbNxZ89L1Aq6BXQ2NadYqfCE1fR6xC5HATQEsSSEpymXFsdi9M6FoeL1Ysn4lipLqmPvF+AAbCX7Vxtkd7UL5EzjdfX1Kk4+QBp0VeRHzmJvNKIsBLabJC5lLGXdBMqRjZOkAicXJNDhb49rTdZ25Q01VVK9Xim9Xw67vmw9gTRpU/mI+sTYznT99HBL2McRFH9R2TZan7d3fcLX58lJLO48lNkBrJMg8UNntpoTUX6ZHS+rSd7pbxQmh+fZa2z/73qfQ6ECXvKfSs0JoVVztKxe6lzAFYHRkMS8W17zi04PvHM17aHpVe399250UowAUAGmoxAU+GzwAKHUEaRybXlb1zbbSm7M73kTNB+IzsY5jKi/nn+w5ITRVffbSbH/vkwZ8G5hreVMswqtLxvl2wScelnOh18KJMlPcq/k4IsPUJ7LE/RbptlAJc6ukul3l9M87kcDfInO3SvEy9PcPZ6zTHrMzL5+NYkEiNbss7y4Z0dI9t4PNE/R8MkDsAjcT4Zf/z7sDy1u8rJO+14dc9v79bix0SNXPOXlDLAVwOvOwbWiu4XXcbS68RRSp721PEyxVoWDwiFiuDjja/l323v8+r9fP6dMyuRe9zl2GbsNiy4kGq3hcVBzGYY2BFhxTl3pIspVO5j4Q/EDEXGnJmsiov+/JDHMK+RKybRJem/f01nMn90yYnwN90iMzXjhvwo9TXPO7i19bkoswZSfa5fJTLJ7dvLPi4twslQEEhz1mMQRi/zxLhXmDbdx+4z6PuPJjMu5bvBzw20T241vTZAhpW0HEvKNeOzdcQYPiFk/lwOmD5O8x8zL/ncXw30y25cWZK6SxM8kCJWCpvKVbMbvQ/gTVGkWdE/VfT0sufh2rVDKZTVs1Dx/r7qnVAAqSrF5c7dbhSgJxhUIYwWFq2JOiyueaWM14IPELwiALaceo2pVWGRusVZrfaoWoCyMzpDU+1RdzKZA0oHUhVaV9r2ecfYwiMUujZYpCDcNg8UwbVYoFe5YmZxmwA4Yzqu5agZieZ25S9ww01CfEghBOzBpkF615TYADvmeYyQEfpeLvdcPHaKvFoXEyS/o4cS3PF9PWdkZE1lD8nmVrOZJK0Vsa6mQFTRQ8AUpYFzec8F+tWAEAVL047Mnsqlqyb0p2QTUZcDWAKBXQoN5luPXfj0TvGIekjC4zstmRkjTlOgHgMGH/a4D8kxsrAId87fSev9fOrpC+VlvT7I0uqfZz2zRV4fEh2fOzn6SEeYJG7/twROfpYEDwO4PjV7ynbNxZ8ROChYoxIti6sg/AgdgLq6PnR9fNESloDy2II0PFIcJX5nGDkS5eY3ELAVE03AFPqb772dF/FXbEzVkR9JDjZrzvCG/a7aqBlFZ2CVrUosGvyz3pfGS/STVuk1ePQgipqGp2O2IRcOr37ZmAumRaa3HndhmFHFFKcmaPLq5ZKXcc1jdv08mSrBy+mY0ym9kqcCNPYJOZL5zFGBr32Nl6PDV+UyySgj6RVtl5wiFcKTuBhekbvYHAYUEtXmYIHAWCXhm/V62T1AIBdGw6teNcvQa1e3BJQNrMUvNQde93RL7aJv9kO7LVN1Ny5dZEAVMq5hSVPtT4Et/qAZ0FI4PFmOyJCnho+AxdDiFZFv/TIjPhQED0DNE8tuPZRTfhwMPLSNnx5XIKy/jhHZWEBUDadrkWgQk2fAbMc8zxXVy9Bf2sbbm3M6ZvtwGf7Fb/p+YuYrww2c9YRuVz4+cu5T2CziIHMlgJmN+m41IbT3Ul0r0WKr/d1LxajsieXHD9Ht3kbUTLWWDGY4HmTHnEla7wPSg/LC8dPmuLcKlqDu0HE2EObQK/V9pXDrB2FVa3ZBEP79z1u1cpxWqbc2SqOoriWDdJtfXHebmeNmBCIGs5yKnWzRFtO/1qLBiqJJRqTZVoahmWWfV3bIxCVN7KUHQfA6mIRlKwAg/FsKfhVkhx4FesMzfdO8Vrl56uAL8unPEW+f4pXGi8KI8Nr/tm95/fV9o0FHwAgljcaJp+pKR6oq4+vo699zUWdv1wOWgvIrfcS3IM9Q4qPOxECclX2PgQYFxAynycB0Pj5I/OcvnK/NY32/r5iqDcY8DQWLzfITHD0qDHWg35iHtt5LaK/19pHjtOwDCWtEZZat/oko6u5mvCi4QDpZU2kOo+6xgBV1cc+eAsG/fA4ASY8wiwND6CTkdVwasFeG95uB97UAxevVrpWKo3rSbfvi1GrF3fCn8kUf5biLhoTprdeHwIitq5mcl9jHEYNGx8bMbsf5z3zUnDgsqVsGldRSO3QUmIuHo0rr0nz//t+CWF/65sBm9THXCqe59MqmInPAA/YxYjDyCmybHSNsApsdZBFYU13UEVHc+CAamC0QNCFHDiUSvM4E7RHrZ9WcSuKrWyvWs0ezdv6GcFKSxuVuXEazlQ0sHmWD7NYMtCJ8fBjV5ebSGJABWK/td8fvPc6FItpT06/q8Bq6FSLRWFmWY7DUQdsU28kbeQPxifHtWk6VtLnSL9PilHq23TPFVSlz17ddh9pXByqEGTLuE7nf9g9EwBkvebSZSpXkpTShwrZpKjpfd8/0L7R4CMEbo64BYapJw/Mo7YgSeU10/earSnK4jr+NUHCgl4FmAed10r300p/pnWY6YN3AZSPJmt9pjQOooiI5OnFEJlNY+s1yHiarvnaOE337bB6BwXA1uPYNdAPuDftTrenhuzmUfqxAxExzx4YC3sdkw/gpAzQpjx8laCj58ladDIVTlpEjicSG2vhhpT6RBCZC1JJg7FSeh+ZERGF3OqsfeYUyWCXDJ/9aVYKP4dWppe24+12w6+/fImncuJtvdmmmzqXg0wLFN+q1xQrYdaBQ6vxZZTd3BJqXCLXwyrBxtwuQaF1UQJyvEeuMcJnpIAIDVgHXwYwx3tMrobSUcU0ZugAGTZWZboHBeJL2/H58Rzf3XrFS9sDGLRecLbiSqVZ3pTvJQRl8yyddK81WJTzsCUXBJ9JVfDZfgt3CNNxKzqeyhnxN7s2XIplHTUV3PqGKi1ASJGO3utwH3TjT2GFY4XVm2EaO2NzHsWi8BnuXC6YGW8BKypn47ZN83WcmxkktgFAVovdGpMivnnexQEV9X1b7F0r4+UL5QoLAJn2OaA8NeyXE292y0h6sx3j+s2scwZKshJi9446RKmxPlF8J7CswIiwZd9k2l+kJKVOdPAF9Qf7F/ux7K+rZqziuGexIGQQYCBnyKu4XMie5X6azsv7nWJkGMX+N64r6ZqTrHnwTJJk9Me2by740DRwqzCNEUmfE6Q8EqKrtFrQtnCVU7h9ADm+dk1df+kPsjoS4lxRswgGuOBX68LyonT5Xc6La/I7LIs6NHdHQcFkIbj/SaDjtOdK68DphEzOShoR//421jQo5Ing5nj0YTuMoMKwoqQBWcjF7uae/fuIBf9wA+ALl6+Vrk0L2wRAc19WcOY/VWBjrCZwnzZL8yzwmA8ZZvzVJ78CuPxduD+KbfAXHS6RSJ0Esyo6KvJ82DV3nOhacCxxJ+/bjpe249ZrpEJvtUc2Sq65cj1MUL7c5ngJFoRjGqbAgEMpqQy9Wjlz3nctulbWf86K2hk4B8HZzA3wvu24lNOydNocIMnrZ0G7ifF1hJWuGMBCGcFMUXOmaGKQfSDEMWIsOGfk6ni73UA2UQIWpuE2GODLwt4AnwWp0v1CCwoznvIzTRbYNK4bELE5OXso9//sFRVmiVnjgg5U5MJyfE7Of8F4X2OdyljDLOrG3+3eCB6QPtT1e4WegpYvEN/r6aAHr50TlT1yWRL4zVasXJzRfsZ4eqC9iBo4qXFbVy4kticpdIM8cAmrmOafn40XunvwVz7L58QDLcdgBkK818Mm4zmQfi7dnkBGNAKs9fMEVLhHEnRpkTmM4CvaNxZ8SNcQLmvhMFokhrVBLUMDGCbfRWAE0sP4fBLyfZyTM1getTtZlAWkGwfMnC/3sSgynxMaNPvWB6K+Q8V1zkE3oCIsuTJpDtNYgmhdIGrpo3cLN/fHM0LEmUbjGazSOLCN4LcpqE1HfEcEovlGbjUmfCPLt6S1RmUJQJOYi5ijR8I/86esAGoFMAm0cE3ldWIMffO85JgXLH0IC4tvorRyPe8nPttv+PZ2RZGOs9cQ9K+BDeAejBTRCFQsWixuo57BC7K7Lz+DjgpF8RF+FtMIyW76ohvQ4TEbFe/OC17ajnfHJYIL3+7HFBDKNNz3tx3nWfHy5SUtWmYyCOQoRpW/dZTnBmwtrCHVGW3Pbtwcp5YATAAiawOteiVdoxkXGRv/2Quu54Z35wVnIVfJMP9ny8mUKiqKt9vNlq/04DaRVnBw3kS94m6P2jlrGvCUWiucr3SMC62nkq1bPbKZTtSI82Bj1sv4WaJib3YVrcHHvTurqFtgLqVFVhL7ynb0ir1Y7M+GHnwwub3H7uNjYGHzeBBaKy/OapsBMQHHrVlK8J3Vy8Fd8bnUXiYdwx4okwrayxVXSGALSK+dIgJO4z1J71L3KsU2hyNQ18YSc7aLg4mhbJp/VqUAzllh+07ai3T5N4GDWVJr0VE4L8mvofAuTdMllr1/+my1DD9CIdzDpuvLfA6VraUv2bozXYvypWBkAsoAneD++ZHtGws+YiKScM5WEH1t0hekRkEfVNp9HJLBynSZdQE8ura+8nvqJkvS5+vFOszPsyLdFf2ne9jCkOivaJpwTR9O4Iz/HgSndkzjGZp++ldOMZIgd79wzCIjgJu+b6CMPs8xDoKhjcU7BGD1E0+IcDHHcnxiuAhMiNL7CMiNy2VgmD/Lz+j3zWMxFf18tNEA83oRA4dIwYvdEWzH0A6LWEE3/s7GVEwKr5n/w+IeuNlWUadOJ332CCis4ETN/vwiHVUHYLmUM4TyUSv26mnA9QyXAgDUbhkx7dniPIozmLLYnFUPLUan7uuubg3bZsGlLLZWRS3FmCyftBz4mim+iHPAaqe1rhjB1c3LpQPA9dzSs9m1LqUN0i+Y4O1Jgr0W3BsxHt2qvTYVdAaPouJF9ogj4diY9cksHdXBdaa85+cxh5hp7fnZ0euIG3EQkvuVtXe2lfsln5PjaQrmgFO6Wzokxv7Q6tTkNYJn2ViPZorVAXBLlhkGQLNwXlv6RgsIVA0Y5PdRZbx3eR945X3zLQy5Pk/HiLeBWpbZrVdczw23sxqlv47r0/0d+6lfVABoxIT4D5W50OSH5AEeAAqVh8c9PETnnx8aBwIGyoEc46ZUMP00CwR9xUqSPotrrc9J2VDSuJXUUcUIOD0VJXnAvqp9Y8FHtm4AmAaE1g4Aw3c/nZxARVgxdJjQFJB1Uh8tkBV9PujLhMgfLMa773hC8hs+bPnePNYXXAjXnFqczqHcjkWDO1Ce7pPQzwpwiNJP00m6wthF/bhMdJV5LFoXlK+TI/tICyBCS+bY2WSSTuW4kL+jjUebsjjTOE0gC2OuxDlNNO0CkocnA710XRWT+VqHZYfjMzGJYhB2UWMHgDf1cMZTCyDtKqkqbfUN1jIL6NsvUFToBD4Ac7PQ2mH36fGzQFClBzNq14Jbqk9icSApnqGYUBRRNC143oyhk26a1kesB4EIGSgJPC7Vrsksl1zfxGIo9jDtA7a+IlYgbXxHs8BYVQlOCgZ1WoCnjR/BAIAQTNlVktuUMt4LujNn1tIBcpi4sBbRYDgtHouyu5uuJoFYxNliMbJcHhV04/tC4EEQAmCyNAjwMOWc5F7rdS0bxj7fpD0EXACC94Skc7w/rxnBz6m1njJ2fC3mVNsrtjlmxlloVdUSCLjx+q/im9Mk9HS8j5McpJtVxrOevWBPsR23XvFybrieFedZI1CW171rMb7GvDwdwv3vQSz3NCxJUXr1PtM974/JlgVeg2PzqNy9AYb76wgwAuz9mKyM0aq+djnvh3mpUHmblLikxFLZK6f904H9v7J9Y8FHCE/ArWHuU+PAQSa3SJahk2BIk3gndAhaOMDp/tMrR+GTAM30d7oGj9f1IjoOm7TsBCzuwM4iHKcCQulnLKQEyniPyXqE5JdMVgV+nhdYKFBJwIrC3ElnQT/UtYzN0xuZXVBniwizNJbU22hOLBYulzxemkyW61iuOxMQREUx/wXzS5Ou9Yi1NcYNiGAzWec4TbpiOcc3AwoVBhwyRiMzmq7CYPXxA4OLYUPDJpYdwbXHwmDNtVc7jxkMdv5kDYH5980tY5aT3UEIY1Om+J3Uv6aCZycyO3cDNTcHVCSaI0PqkeIwCDpoTXmuBzbpEdh4elYNMMcZAC58C4yDIwW5UrPP5+XYqiH0FeeyQDbpgBOWiQyNWJXmfg3Q03pB82c/u2UYbaXj1oBTLC6D8TwZRHJuDUSOgm4G9GbLx+Y1aLZe0V348xlvbUPzFPZauimcZQUm92snrysDv4P5tqHgB+051sO1b7j24XIZ7qs5oHdbXFC5wF7+jAGyR8qWsWBZQTurFXNr/r7TckItWmESk27nvF9GZ+wDbSOjqkz9NuC3l46nzd4CunzU08DtogrZABQHHiwDgA5sBY0Vv3MHXgEu9t3jYpRTWwU7/16vvwATUUS8XuxlDwRVgBeM4bxTqJe/szUkE6Tp0p+s7M/W6DRGguG2/sj2jQUfAGKwKKgnszgF9yqYgBl8+N8x6VnY82tJkyXjmOl6/tWdFo0Hfz9YsPH1im7Xz5CeMfc9Ojm+16IDiPnifKDgzOuViyc9YwCQsrhlFiwQFoYm0JM+6uIVNAeDZJjOMQqgsbx5LXMnNbMevvLyPkLo6/DHM72C2u/Mjgm5zzfDiNtZry/2H1/GsZHwhbQ3l+CLFUW7b45DwC/A4wN2WQKQ4mZ+BpGODJFidTegAUZqLNgW9Nld7fMOpJo8bi1QsxZkbo/VbXD0xDeCYc0hJ8Sp5hK5ti0sIRTYUQ+ltMH6CqAH+Yw/qwvUCEL0Mf/Qnj7zyIxx3EoDUs0PE6Lktliot/V+/JtbcVqRKcOHPCc5sLVIn+rxFFH0KgYs/N8uzVwv2Sqgg7isa8cThnumiOL9OSxCAowCff7ccwbQHGhr151TJs5epurH175PTKu5/lB2E2Zema7iGUEz78fp7sXmmTmTW66VwXTaxoROipHa+6NFBvfF0uLpHFA8aow12zxL7HZsw4rG10JgwCPFhFjAqfVBik5rbtpXp83IfzzOch+H6P3eNCnC6SbTWl8VRNdqs+VCFBOBG38KNMB1Vk4DSGQgFnIls2TPG+RrYyDLXP6aAB82PhJoivTqk4XiA6g0g40JaGSSlwRKQqnNgIBSO6NSpAn0P15FvVnq8z59/L2aHKkFTLwU6X4Tf4UjYnFhCchkxYm027VfXEwfYG1SfxkZDJatCSoATgHq0HiPXn0DHkyS1rbYIGmeP5o6CdBmhbJYtdRJa6ZxoRvlwbBOY+itb+mFTmtDmK3zCjibX6z1Jvc3nlB/up+V4p5N6ZalYtkOt2RaJwgZY3XBtW94KmdYBgBEFoQRZrlZvp6TdtogmPLr4OABqYppEvRN5+DAca8hwAyMDHfOm4IoSkcXgpVyh3EuuAlPVdCZTu0CixYPAg/eg8G0ZznvwMMYc5vk1gqux473teMoIxX4qZ5hgbn1DZ8fzxbn0C0ociJL8yHbq6W11rpHn+2n/etqGntTwXma8Gr7AQWwlx6ZMk3v3R4rs+veN5+PGShkwrHzwY5NV1JVq7JbBLidI1soX6v1gis2HG7VLFA8X2YitwMEizWydHisVbEtaA7OupMA8pgeUiW57/x5zl7x0ja8Oy7m7ji2cMERgCioZMh4bzy1Pu+H6sJf6Zbh+89jCgLA9C4W7CoaXDjFN8NSFDcn8eP9xeMkwmriIKhLMcDhwCrXoGHZeKEmOO23mISwrvtLljtZKK+gY7kOmyjuwQDBCIH5qlCRADEF1T4ERvl+K5C4kxfiirDeH5eeJebqQ5rC0r6x4GOSOpLG/nWZeXf6HeLM5y6CeUacr192whMF5q6A3Au9R8BoFXC4ByOBZnmN164j49y8GD4q4jhpluOakr4bx6jAqtrm0ztsA3At2DbTGn/T/FpcSBdBWEJ6NzZLiw9wcOMBZ5IXcwaCUz9HH6eXRRQoMgWTIX0V4/nKtb6yPTou9dX3CrMK6di0cwpl6wVdFEWqZwb1SKssMgTCsUzgapLfKPyXdKz2FQ/TIGiQD1pa2LKVhgCmwTNuBJH10f3hi4OVs5SIE6DJnq6W+wyf4oJjbENd157A7uPrhSb9TPUNmFZfZbiD4NVjswWnN4n+WAVfRe+Y0kYzLwWDXlsrqKWiVc+EQQYdJcYL8GBOHfEIOcg0p9nmGjX8yX5WUZwcPxlpz9UpyzWNb1zX3URrqXner3gdoUZBmuKBqpt7qxTPdukTtXp/cA7X7KmmfNxaxXHWAB53LVkepne4404WZnKyaatK+4J2jzdKJw+rDfs9gOWdBa3bfqSaOqOp9gub78EqLtuTgKXlfWQ0uizoqd/j0jzkflxeaV/3nFCiNJ33IVmmyz2Wc+/k7aJwrcDj67ZvLPio1w5pGoGE9lOH9v0IiHxgsENA5MVellMexXJgsULEtbw/D4V2+tjRSpilMBampXnptLi4gFaT3LQAiYB4XE+fxzgIoHqXwdG3dD4yMk4oWwisgCD+4rgn02/EdoCbqm+KKdMliJCKC9+0IbCvkqwcq3Zxhxtlni+mBa/+xzEOaZy4aSxzNb2EBZjW0APAGPfwf8GNVgDdjOcjk0xxYTFI8uXcg5uBjZv5y7LTZKHGv3OqYxCKSao94rnEBzZAgXf9YtYOiJOJ1chyAOY4iRycmtvhIOnwlN/3Tt5FIUWARC4TA6GmTd6KuyToPvJLdwiubTOuC7rwWsVxVGhPRd8U0F7QGnBmbo8lFiHXY6Ewz5aWwy1NBMytFeMoUbMaFhn8EMOCYeNc3X2UM3Zy4/xFnI+nwD65qynHUuTMlxF4apYF9vmpnnjuR1g2mldxBTBlwSgMuNyaBQW/3Q/rn8fzbNKCjK4510tXwbVvPmeDZ4TZMejm4mEQ7LVt8YzAIIZjbFNwjtQeFlOSo41Ml8TK6fsP6dWV+80DBUtt0dtp6gLfgUxfaijRkqgqeDk23M5tIg9TLwvBPogAtZqJQgRoLXE6rLKFe2juY8SU2Ydz1gkGZcJyrZxxOa7v+y9lEP97pEjRqu17ZfFnWjmK4niO5QJmct9XQHN3jdzjhEESJv21E/MhZ79DbmEZwN2cfHxTP38BCfG1LGg73WySP2lCsnntYVvvkT9eEXnuSLrXo4OylWAC6/qB8ZH0jK/cVpYxf/zHiLbP/ArcyJdbhuaGbubqV7u3Putrk51A3eu6w9IIuIDZJfWoww9e+uUys8YjiKj0h3EdOirBKkYmCeBZL32Ai+m+SSunVputIMMkPjObGgAxQX1oncDHSnaVBfSjxnllBg1Th2nG5zFnAh4RGKojsLRAra/ubiFgufUafCI0fU8mcB1GX8UAGRULkF0aXQqvNdbyGGNt/4oAurxUmWQrpwrzeTl+W3IBDPKuEQwMYAIetI5N/ZY5pmR1tVhfHj8PrU0TZ4yMjKhdmwEPEVx1tsyUsGJ19OTGo0CPdZAAEZvVbDKg3VXRHQyNTg8gZ53FyMTwatMPGwWyLsck4NPcmgovlNjUaOhbm/lS1rg5annB9fLo/utr8VWbzYPX6M6C8dEb1nLr117RpKSuB4W85PMucmV9fabPFpkyHzhuHTwpD4DWh9o3F3w0o6vtG9B3i/fo7G1+wGkxje8ibiIjaDw4b70ev9NZgX54HB4Ly4woGVsRk7dq4h8QcvMX8/lYrjeZ/z7U+FyPtPvluLtjKLEpaGEv9c01o5e2Rc0PexaJDJe7zbPYP2xqps8LzN8M35TONG6+Ua3WpLCW6GwtmcY6brq8VLrMXVJ6pmfmGnqwXkJpgAeDeaMWf+0VVWiW3nBtNQpebWUwieaWy5YDmMiuRCyS/+xlStd9LgdKMtcdYdG439Gp9WZeh+abchVFc+sMAcNTOScryF5a1Ie5YguyLwagUlMPK5ib5st58WEeBF6HM6v+4HoxDfa6W3AiXVex5gaAfW3cCM7ebjfs7uapyzEGBsb4kmFXVCClY99PK3y3H5G584It2FsfNUtfnl0gQRpW7LynpaotQRc5PgjaMofImvJKQS9+L6YwX8qgr8/xNZyzt+WGvQwyOsCyoJ7KiWs/g2qfINIsFuLuQbOgETTfmHqsBtD22sc4Lo3ul948ALUVz3TBKNzGF9L36rASpHeSy4BCUbf7e+WxP7yo3NmKWzLwOGg5afxWNdkBSNEZeKZ9N/YLfhYprTLtEdM2opj3dIKuhYJ9uO6XnsZeiiQ7ZMi2ta3H83GRsMkkg5L2lvdIDk/NnZw3SEkf/5XgqW8c+FAf/Ha+oN1e0DZBu6pxKGT+hlXArE9P01YfC3d9R3Q1i/ngr4GOd+AjA/h1QWbwEYJLXgUfOQd7FvbLRD8ACzkgi6xz+dmQ8sN7hQU/ttQvzPen2SwL/Mz3wSq6fQO0d7R3V5znDdfTmGWOs+N2AO3FfMcqClT6RaxFTMjR0M6C/qLAIUDzapKnu9mOxFibXuDVwmN25xG4to4z52R6sdbzOV48No1xHJvk+Hos57uLZS20L684+xVHu+EAcPaO61lwfnkzt8K5oZeOXtudBpuLegGYaqvUouiloe4H3p8nam3Y9hO9jMDQHM/BLAVgxBkcveOlFZza8dLm4w8MDb05bbvWc3IPndo8/bShacNxiLsEBvg4Wp2GvjvdNdulWObH0dT6cy04z47z5gyeOcaIm+lprKldb9DSY32d+80EfWs4twOtXyHSUUvDLcbBWmuK1hvOlw3n0dHeGTmadjJxntCtoZ83i/1oFf3Y0Y4Trd9wnjds2wEUc68YY6/XrXFrBYFHV4GWE3U7oXJCEvnZS1OcKDh7n7g1GtmAYYGit9ZxO4F2LdBe0c7qQkTRzhuwH9DSLOtNjIVU6gmVjgbFWU4cxw2Qhlt1llcoDq92fPSOo1uKfNcWhoWzNTQUHIfNz+0qbk3YIhh38/c6Z92YFaKiK9DOhtYE7dYMhNwsuFwOS3uVJiiHoB/jvVQqAAv4CLdGE2hT9Noh2tAuV7St4Tzs2UQU59FxnD6/PrdBWNeHGw/VgEY7OqR0c2W04pk5BTgMLNl+ZKAJpwy5wuXJRY7R71e/h+23onatR4rmI0Ne3tMeWSvWm04gI32fP7/bT1/Z9wJ8JFm29k1Ok83tptDri523gqhHXdaPOeqvYfs//o//A9/73vd+2N341D61T+1T+9Q+tU/tr6D90i/9Ev76v/6v/+Ax3zjw0XvHL/7iL+J3/s7fiV/6pV/Cd77znR92l/7/qn3++ef43ve+92nsfwjt09j/cNqncf/htU9j/8Nr/1+MvariBz/4AX7Lb/ktKOXDcQDfOLdLKQW/9bf+VgDAd77znU8L8ofUPo39D699GvsfTvs07j+89mnsf3jt/+2x/+53v/tRx32NxJhP7VP71D61T+1T+9Q+tb/69gl8fGqf2qf2qX1qn9qn9te0fSPBx9PTE/7oH/2jeHp6+mF35f/v2qex/+G1T2P/w2mfxv2H1z6N/Q+v/bDH/hsXcPqpfWqf2qf2qX1qn9qv7faNtHx8ap/ap/apfWqf2qf2a7d9Ah+f2qf2qX1qn9qn9qn9NW2fwMen9ql9ap/ap/apfWp/Tdsn8PGpfWqf2qf2qX1qn9pf0/YJfHxqn9qn9v9r795ConrXMIA/ajppppONOmOhqZlSHijLYYgscPCAhGUXZl5YhKKN0MEkDNLqxjDoopC6yy7CSsh/JBWYR6zR0hRTS1QsqRwlxbPm6d0Xe7vYKy1t517jDO8PBnR93yze71lrPl5riYwxJqlV2Xzk5eVhy5YtWLt2LdRqNd68eWPskszK5cuXYWFhIXr5+fkJ45OTk9DpdNi4cSPs7e1x5MgR9Pb2GrFi01VVVYWDBw/Czc0NFhYW+Oeff0TjRISsrCyoVCrY2tpCq9Wivb1dNGdgYAAJCQlwcHCAXC7HyZMnMTo6KuEqTNNS2R8/fnzB5yAyMlI0h7P/czk5OdizZw/Wr18PFxcXHDp0CG1tbaI5y9ljuru7ER0dDTs7O7i4uCAjIwMzMzNgi1tO7gcOHFhwz6ekpIjmSJX7qms+Hj58iHPnziE7Oxvv3r1DUFAQIiIi0NfXZ+zSzMqOHTvQ09MjvKqrq4Wxs2fP4unTpygsLERlZSW+ffuG2NhYI1ZrusbGxhAUFIS8vLxFx3Nzc3Hz5k3cuXMHtbW1WLduHSIiIjA5OSnMSUhIQEtLC0pKSlBcXIyqqiokJydLtQSTtVT2ABAZGSn6HBQUFIjGOfs/V1lZCZ1Oh5qaGpSUlGB6ehrh4eEYGxsT5iy1x8zOziI6OhpTU1N4/fo17t27h/z8fGRlZRljSSZhObkDQFJSkuiez83NFcYkzZ1WmZCQENLpdML3s7Oz5ObmRjk5OUasyrxkZ2dTUFDQomODg4NkbW1NhYWFwrEPHz4QANLr9RJVaJ4AUFFRkfD93NwcKZVKun79unBscHCQZDIZFRQUEBFRa2srAaC3b98Kc54/f04WFhb09etXyWo3dT9nT0SUmJhIMTExv3wPZ78y+vr6CABVVlYS0fL2mGfPnpGlpSUZDAZhzu3bt8nBwYF+/Pgh7QJM1M+5ExHt37+fTp8+/cv3SJn7qvqXj6mpKdTX10Or1QrHLC0todVqodfrjViZ+Wlvb4ebmxu8vLyQkJCA7u5uAEB9fT2mp6dF18DPzw/u7u58DVZYV1cXDAaDKGtHR0eo1Woha71eD7lcjt27dwtztFotLC0tUVtbK3nN5qaiogIuLi7w9fVFamoq+vv7hTHOfmUMDQ0BAJycnAAsb4/R6/UICAiAq6urMCciIgLDw8NoaWmRsHrT9XPu8+7fvw+FQgF/f39kZmZifHxcGJMy91X1V22/f/+O2dlZ0cIBwNXVFR8/fjRSVeZHrVYjPz8fvr6+6OnpwZUrV7Bv3z40NzfDYDDAxsYGcrlc9B5XV1cYDAbjFGym5vNc7H6fHzMYDHBxcRGNr1mzBk5OTnw9/lJkZCRiY2Ph6emJzs5OXLx4EVFRUdDr9bCysuLsV8Dc3BzOnDmDvXv3wt/fHwCWtccYDIZFPxfzY+z3FssdAI4dOwYPDw+4ubmhqakJFy5cQFtbGx4/fgxA2txXVfPBpBEVFSV8HRgYCLVaDQ8PDzx69Ai2trZGrIwx6Rw9elT4OiAgAIGBgfD29kZFRQXCwsKMWJn50Ol0aG5uFj1Txv7/fpX7fz+vFBAQAJVKhbCwMHR2dsLb21vSGlfVf7soFApYWVkteOq5t7cXSqXSSFWZP7lcjm3btqGjowNKpRJTU1MYHBwUzeFrsPLm8/zd/a5UKhc8bD0zM4OBgQG+HivMy8sLCoUCHR0dADj7v5WWlobi4mKUl5dj8+bNwvHl7DFKpXLRz8X8GPu1X+W+GLVaDQCie16q3FdV82FjY4Pg4GCUlpYKx+bm5lBaWgqNRmPEyszb6OgoOjs7oVKpEBwcDGtra9E1aGtrQ3d3N1+DFebp6QmlUinKenh4GLW1tULWGo0Gg4ODqK+vF+aUlZVhbm5O2DjYyvjy5Qv6+/uhUqkAcPb/KyJCWloaioqKUFZWBk9PT9H4cvYYjUaD9+/fi5q/kpISODg4YPv27dIsxMQslftiGhsbAUB0z0uW+4o+vroCHjx4QDKZjPLz86m1tZWSk5NJLpeLnr5lfyc9PZ0qKiqoq6uLXr16RVqtlhQKBfX19RERUUpKCrm7u1NZWRnV1dWRRqMhjUZj5KpN08jICDU0NFBDQwMBoBs3blBDQwN9/vyZiIiuXbtGcrmcnjx5Qk1NTRQTE0Oenp40MTEhnCMyMpJ27txJtbW1VF1dTT4+PhQfH2+sJZmM32U/MjJC58+fJ71eT11dXfTy5UvatWsX+fj40OTkpHAOzv7PpaamkqOjI1VUVFBPT4/wGh8fF+YstcfMzMyQv78/hYeHU2NjI7148YKcnZ0pMzPTGEsyCUvl3tHRQVevXqW6ujrq6uqiJ0+ekJeXF4WGhgrnkDL3Vdd8EBHdunWL3N3dycbGhkJCQqimpsbYJZmVuLg4UqlUZGNjQ5s2baK4uDjq6OgQxicmJujUqVO0YcMGsrOzo8OHD1NPT48RKzZd5eXlBGDBKzExkYj+/eu2ly5dIldXV5LJZBQWFkZtbW2ic/T391N8fDzZ29uTg4MDnThxgkZGRoywGtPyu+zHx8cpPDycnJ2dydramjw8PCgpKWnBDzmc/Z9bLHMAdPfuXWHOcvaYT58+UVRUFNna2pJCoaD09HSanp6WeDWmY6ncu7u7KTQ0lJycnEgmk9HWrVspIyODhoaGROeRKneL/xTNGGOMMSaJVfXMB2OMMcbMHzcfjDHGGJMUNx+MMcYYkxQ3H4wxxhiTFDcfjDHGGJMUNx+MMcYYkxQ3H4wxxhiTFDcfjDHGGJMUNx+MMcYYkxQ3H4wxxhiTFDcfjDHGGJPUvwCzmGu7BYfsVwAAAABJRU5ErkJggg==", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "import matplotlib.pyplot as plt\n", - "plt.figure()\n", - "plt.imshow(processed_example[\"labels\"].T)\n", - "plt.show()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "bWMT9X6w237M" - }, - "source": [ - "\n", - "If we run a vocoder on the log-mel spectrogram, it should produce the original audio again. We'll load the HiFi-GAN vocoder from the original [SpeechT5 checkpoint](https://hf.co/microsoft/speecht5_hifigan)." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 81, - "referenced_widgets": [ - "a60987317acd40278489533a2d9dd021", - "c9662066695c43e7901ba019a0dc9e8c", - "4ca762251949444f921863535a18e5c5", - "d7142a382f884564921bcfcf65909287", - "13226fa6805041fdb7e3976e4577a66e", - "7c992442c78045e0962299728b49bbb5", - "a5fe768b739d4df896d15370e981b656", - "4a7bd718c8874fc2bbd7a566e1da124d", - "ea8fbaa445bd442b82bb60a67b0efcea", - "db1394f796f84b5295e16f1f8b2a526a", - "f44278459f804c7e9412f72c8cb4eef0", - "33e739de4df54f96a276027d2d1f66ea", - "2d3eb78c7b994f3cb2d57d80458c35d6", - "de8ee1e97a0f4bbfa17281a0c067b5b1", - "5ab5b7305633479494e991c26c2268a9", - "ab27bce16ed24effbddb7596ffe2c3c1", - "5d30def7a2bb463baa858eb0eee9d094", - "06508d700e9c426b85f374381d3439d9", - "af4aeb90cfbc4937860ffd47ef7987e5", - "8b5abf1e77284e549e1ed7cdd100e2af", - "e550d62c5fb54e8c9be548e252a4ddc3", - "b51084470848412d9360ed3487aaf3f6" - ] + "d7cd149116154f98aad430d857c46381": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } }, - "id": "2Yu-rqwa1zns", - "outputId": "3b909915-c86b-4ee3-d2bb-12b1d2b2ede6" - }, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "a60987317acd40278489533a2d9dd021", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "config.json: 0%| | 0.00/636 [00:00\n", - " \n", - " Your browser does not support the audio element.\n", - " \n", - " " - ], - "text/plain": [ - "" - ] - }, - "execution_count": 22, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "from IPython.display import Audio\n", - "Audio(speech.cpu().numpy(), rate=16000)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "RPLVad8w3CvV" - }, - "source": [ - "That all looks and sounds good! We can now process the entire dataset. This can take between 5 and 10 minutes." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 86, - "referenced_widgets": [ - "2ebee62340c24076b6edeb96d233b5e0", - "dc0e721504184b778486802d47239e00", - "4744d62b21e645b8bad84578aed387d3", - "ef635c73df96463ea145fad659b04028", - "00adec96a5654f3a9d08c8331366f704", - "3fd3b45e98ff4292a1444f89fc6ae95e", - "876341d2a2484e60a72caad3dc02c1b4", - "4699dc096aa644b6add210252efa7334", - "f2f329976e13413c9bcef0e56280d563", - "bd10c6180edc414f877b5ac363801a42", - "b818deafc75f4bfa8139ae6192dab50d" - ] + "869df80d498642f4b3a1d1825372cef7": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } }, - "id": "ekis02SC2hBN", - "outputId": "dab33b54-b3a0-43fe-b624-aab4ec391873" - }, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "2ebee62340c24076b6edeb96d233b5e0", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "Map: 0%| | 0/4112 [00:00 600). Running this sequence through the model will result in indexing errors\n" - ] - } - ], - "source": [ - "dataset = dataset.map(\n", - " prepare_dataset, remove_columns=dataset.column_names,\n", - ")" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "7z_QGJ1u3LTa" - }, - "source": [ - "Some of the examples in the dataset are apparently longer than the maximum input length the model can handle (600 tokens), so we should remove those from the dataset. In fact, to allow for larger batch sizes we'll remove anything over 200 tokens." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 49, - "referenced_widgets": [ - "2993094c7ff6425eab9bb0b1bdf1d7ac", - "fd6cb6748b1a4d83bbd3c1f9bc9293c9", - "a15ad78eb7e249a2ae8f1a4e0b0e359e", - "39f6a7a3035a4c53bebc34e7a90ad14c", - "078823ec9ed64a58abc1ee0a7d55976a", - "b710b2c93fcb437eb220dbd57ba1a235", - "4acb801fd07e4e1db048921d83fad83f", - "3bd4aa82001248acb3758f0ff98fe64c", - "494b73ce426e44da9601305d859f484c", - "c350945401cb48968758c0674598a855", - "0194367f515647b1ae5bc638d212c2ce" - ] + "e74722fed6a94c5bae623ed75c362a45": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } }, - "id": "Sy4kcOco3Ks3", - "outputId": "516034d9-6b6f-44ff-d18a-452e18dff79d" - }, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "2993094c7ff6425eab9bb0b1bdf1d7ac", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "Filter: 0%| | 0/4112 [00:00 Dict[str, torch.Tensor]:\n", - "\n", - " input_ids = [{\"input_ids\": feature[\"input_ids\"]} for feature in features]\n", - " label_features = [{\"input_values\": feature[\"labels\"]} for feature in features]\n", - " speaker_features = [feature[\"speaker_embeddings\"] for feature in features]\n", - "\n", - " # collate the inputs and targets into a batch\n", - " batch = processor.pad(\n", - " input_ids=input_ids,\n", - " labels=label_features,\n", - " return_tensors=\"pt\",\n", - " )\n", - "\n", - " # replace padding with -100 to ignore loss correctly\n", - " batch[\"labels\"] = batch[\"labels\"].masked_fill(\n", - " batch.decoder_attention_mask.unsqueeze(-1).ne(1), -100\n", - " )\n", - "\n", - " # not used during fine-tuning\n", - " del batch[\"decoder_attention_mask\"]\n", - "\n", - " # round down target lengths to multiple of reduction factor\n", - " if model.config.reduction_factor > 1:\n", - " target_lengths = torch.tensor([\n", - " len(feature[\"input_values\"]) for feature in label_features\n", - " ])\n", - " target_lengths = target_lengths.new([\n", - " length - length % model.config.reduction_factor for length in target_lengths\n", - " ])\n", - " max_length = max(target_lengths)\n", - " batch[\"labels\"] = batch[\"labels\"][:, :max_length]\n", - "\n", - " # also add in the speaker embeddings\n", - " batch[\"speaker_embeddings\"] = torch.tensor(speaker_features)\n", - "\n", - " return batch" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ffNanldmrlbD" - }, - "source": [ - "In SpeechT5, the input to the decoder part of the model is reduced by a factor 2. In other words, it throws away every other timestep from the target sequence. The decoder then predicts a sequence that is twice as long. Since the original target sequence length may be odd, the data collator makes sure to round the maximum length of the batch down to be a multiple of 2." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "CJKY4DVO4khr" - }, - "outputs": [], - "source": [ - "data_collator = TTSDataCollatorWithPadding(processor=processor)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "McZfpBzL4mRK" - }, - "source": [ - "Let's test the data collator." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "78-XVnD04ouJ" - }, - "outputs": [], - "source": [ - "features = [\n", - " dataset[\"train\"][0],\n", - " dataset[\"train\"][1],\n", - " dataset[\"train\"][20],\n", - "]\n", - "\n", - "batch = data_collator(features)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" + "0ba493d747144e1daac6252c6accc886": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_9ecef1d0b473411b914eed7fa043478e", + "placeholder": "​", + "style": "IPY_MODEL_d827d96e5328476c80a212fad5570c78", + "value": "added_tokens.json: 100%" + } }, - "id": "vuWoBSpW4pY9", - "outputId": "cfaf09be-cef4-4328-f96d-8c3eda7ec71a" - }, - "outputs": [ - { - "data": { - "text/plain": [ - "{'input_ids': torch.Size([3, 106]),\n", - " 'attention_mask': torch.Size([3, 106]),\n", - " 'labels': torch.Size([3, 580, 80]),\n", - " 'speaker_embeddings': torch.Size([3, 512])}" - ] - }, - "execution_count": 31, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "{k:v.shape for k,v in batch.items()}" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "sVMpz-tpP-vw" - }, - "source": [ - "Looks good!" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "_iOqGsqq4uJv" - }, - "source": [ - "## Training" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "uQiZlXN9ICmc" - }, - "source": [ - "It's always a good idea to upload model checkpoints directly to the [Hugging Face Hub](https://huggingface.co/) while training. To allow this, first log in to the Hub by entering your Hub authentication token:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 145, - "referenced_widgets": [ - "9defb63d40414377962be7a45fe04863", - "4bdb55d30a0b4b648c082f2cf5921383", - "b9d136e1b7944a08a3b206be697e8bcd", - "9a84e7b2ed2e4854b3a27c4a7a6d7b29", - "17f05d9f756e466eba646e8dca6a89e3", - "9d901610487e4d7389072038d0e5d72d", - "8e0bf7d4611641c091e87fbacbf10a19", - "c4660f3058d14daba1940d89e200b65d", - "31ed87b6e80b4822b430c51ae043edcf", - "4edcc714fca4485190e973ed83325af1", - "8c8333ae0d3d4ba7813d4d91245823db", - "7dc5299d9e264f4d9dda9ff552d5d5cc", - "034918f3b833496397f34caa9a0bfbb4", - "0a595220c4004b6ca316c47babe4e5a7", - "1e34bc54a39b42b1a5a2ece20823ca3f", - "efeef3aa079d4bf4bc4c5049f9c74e16", - "821bc686077d4d4faf73a98e60ef2262", - "e6a2cb79b3a14ceb96e44b93529a1b17", - "18f235d673c1422abc9a7a897295aaf4", - "e87df5c1d1fb4d19bd7e8663f39a9073", - "346edbb27fec4479ad74331561fe6d4f", - "382582721b924a77a6ed9ebf2d0e78c6", - "f1e85d48269a4675aa3eb1484d5ebbf7", - "bd810380dabe446d874fbcdbf0a2a815", - "5942dd51d8014d32a6400698fa84f88e", - "813e7e5696b84a0091524b551d94b1a6", - "59f995c679f843eba17be9f2cab2b5ca", - "aa7bf7b3cc7441888151beffb6d30321", - "a903a041f8f34e95b7eb95e7680e68af", - "499ae3562b0e4636a5526230245d502a", - "c5b791315d534952b9087a66d94a49a4", - "d3d5fd89f4df4f278529a4d959f64d5f" - ] - }, - "id": "1z3DEgUOIBz7", - "outputId": "ade902b9-4eda-4a99-fd24-3f62259bf680" - }, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "9defb63d40414377962be7a45fe04863", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "VBox(children=(HTML(value='
\n", - " \n", - " \n", - " [ 2353/10500 41:28 < 2:23:44, 0.94 it/s, Epoch 20.28/91]\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation Loss
5000.5782000.507094
10000.5248000.486292
15000.5125000.474619
20000.5081000.472668

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" + "d827d96e5328476c80a212fad5570c78": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n", - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n" - ] + "22f4b0480fd34920b9a2e0c9d8c609dc": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [10500/10500 3:07:45, Epoch 90/91]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation Loss
5000.5782000.507094
10000.5248000.486292
15000.5125000.474619
20000.5081000.472668
25000.4967000.468271
30000.4905000.464520
35000.4794000.466818
40000.4829000.464720
45000.4770000.464455
50000.4637000.470984
55000.4743000.468265
60000.4595000.469457
65000.4735000.468382
70000.4613000.472399
75000.4678000.473160
80000.4538000.472332
85000.4536000.474660
90000.4587000.473995
95000.4536000.476193
100000.4606000.476838
105000.4528000.479585

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" + "3f9e48a1f9014418825baa991e0f422c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n", - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n", - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n", - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n", - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n", - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n", - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n", - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", - "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", - " warnings.warn(\n", - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n" - ] + "cdb0d85e5dcb4d5998049b784acb00be": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } }, - { - "data": { - "text/plain": [ - "TrainOutput(global_step=10500, training_loss=0.4873873142969041, metrics={'train_runtime': 11266.2505, 'train_samples_per_second': 29.824, 'train_steps_per_second': 0.932, 'total_flos': 2.251261023307164e+16, 'train_loss': 0.4873873142969041, 'epoch': 90.51724137931035})" - ] - }, - "execution_count": 42, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "trainer.train()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "4z3CzVGSs000" - }, - "source": [ - "If we do one more `push_to_hub()` after training we can get a nice model card built for us. We simply have to set the appropriate keyword arguments (kwargs). You can change these values to match your dataset, language and model name accordingly:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "NpXOJAZIs2-n" - }, - "outputs": [], - "source": [ - "kwargs = {\n", - " \"dataset_tags\": \"m-aliabbas/common_voice_urdu1\",\n", - " \"dataset\": \"common_voice_urdu1\", # a 'pretty' name for the training dataset\n", - " \"dataset_args\": \"split: train\",\n", - " \"model_name\": \"SpeechT5 TTS urdu\", # a 'pretty' name for your model\n", - " \"finetuned_from\": \"microsoft/speecht5_tts\",\n", - " \"tasks\": \"text-to-speech\",\n", - "}\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ooEluBcXs5hJ" - }, - "source": [ - "The training results can now be uploaded to the Hub. To do so, execute the `push_to_hub` command:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 156, - "referenced_widgets": [ - "456aa13fa38c4c01b9f43570e31556fe", - "ec7ac27d32c44b40ac8fd18a7700962d", - "fbeb5a0f2394434fb67644f452dcb6b2", - "f22ab8b84c9a406d9383a1253576cf62", - "3915aa47172546afb3f09ea1f7c5b947", - "308b5dd72e6f4ea39d9be4c2e4a02512", - "9aa2c30314774289a458d92cabf2e9e1", - "4d5bdff9982e40138888bc9c72f9233e", - "2c9002098b114841b511b97c5fa39f14", - "fe75e4e2a67749b49efe29817c9148db", - "1660e3387e094116b87f3a8f04782124" - ] + "aaebe1f70f4f4d639d3ecbba9f406f8b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } }, - "id": "mpodV89js9KT", - "outputId": "ecfd3656-aacf-4f48-f2bc-718285ecdcc6" - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", - "Non-default generation parameters: {'max_length': 1876}\n", - "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n" - ] + "992902679da84067b429893c7870b816": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_af9cb18856474687a449ac515ede62e8", + "IPY_MODEL_db44aadde79b40f1850078024e910183", + "IPY_MODEL_f16031daae714a0181ddd0b31471f060" + ], + "layout": "IPY_MODEL_e7bdbfe7797a4b5db827f5b810d2d79b" + } }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "456aa13fa38c4c01b9f43570e31556fe", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "events.out.tfevents.1721676197.d34fde1d2e44.268.2: 0%| | 0.00/101k [00:00\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_pretrained\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_pretrained\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"your_model_save_directory\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py\u001b[0m in \u001b[0;36msave_pretrained\u001b[0;34m(self, save_directory, is_main_process, state_dict, save_function, push_to_hub, max_shard_size, safe_serialization, variant, token, save_peft_format, **kwargs)\u001b[0m\n\u001b[1;32m 2476\u001b[0m \u001b[0;32mreturn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2477\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2478\u001b[0;31m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmakedirs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msave_directory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexist_ok\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2479\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2480\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mpush_to_hub\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/lib/python3.10/os.py\u001b[0m in \u001b[0;36mmakedirs\u001b[0;34m(name, mode, exist_ok)\u001b[0m\n\u001b[1;32m 223\u001b[0m \u001b[0;32mreturn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 224\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 225\u001b[0;31m \u001b[0mmkdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 226\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mOSError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 227\u001b[0m \u001b[0;31m# Cannot rely on checking for EEXIST, since the operating system\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: ''" - ] - } - ], - "source": [ - "model.save_pretrained(\"\")\n", - "tokenizer.save_pretrained(\"your_model_save_directory\")" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ojrUgMeEs_LP" - }, - "source": [ - "You can now share this model with anyone using the link on the Hub." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "5K1AQd8B7b-p" - }, - "source": [ - "## Evaluate" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "TrqUYy3-Qr1w" - }, - "source": [ - "After training finishes, let's use the model to synthesize some speech!\n", - "\n", - "I'm loading the model from the Hugging Face Hub, as the Colab notebook was terminated before training finished (which is why it's a good idea to use `push_to_hub=True` when training)." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 113, - "referenced_widgets": [ - "af584652d0304a899e66314d61726323", - "3b74fdd0043949548e50b1d87413505b", - "958d0637ccad4af49815a2d137fee333", - "e10a5c2d674c4948978e0bc3fc2e8b0d", - "68a15f79b7ab42eaa0b14086f2b54ed6", - "6916935a59f94d6e95449be55732c80c", - "cef8c2e1224b4f0eb21e4963d53431b5", - "7597054472514485afa120d6266c91a5", - "6035b946f770456fbfd123adbb5e3be9", - "64eb31cf8d59468ea56a8e58c71d8122", - "0900daeba5cf4cb29d00a9c5ed5ad330", - "054b003700514935960c7ee0895b8c8e", - "2dcbcbfcbb3c455a8beee0d7f4c12c05", - "be44a4398328449daebb6bd48e2519f7", - "bcd4e9d178c944f6973b2d62fa1e5538", - "d8419ef35db5403c862e8321572ad376", - "af01cdbb16dd490984a749d2da6eff34", - "54783e715ad0408eaa512f7d28a374b2", - "d0f6e0eefec74d9aa2a0a00868c77a55", - "bd858f248a124f14833b044f7b0b71e5", - "d432e91ec63b4655a50bc775ee74aab4", - "af1e15c4f52e4ea5886d1631de2fbe39", - "a617fca4345c4d21a6c44d5ef8246f91", - "3109d5c2ffe04d5ebf296cc26a334a38", - "4d97d63c12ab4c37b53207cf91ac9794", - "a3f2bf1d001c4f2d8571d2a4db8972d1", - "e27fcac6c1be4ecc89028aa8368e6e89", - "c1b4ea7cfc0d434dbb68027af48a5f07", - "5e1fd59b51d1459da614ab5d51116d59", - "ced524c3f07b40e792db0bf1e9c3fe92", - "b257195cf3314cb4bc3aeddc4da142b9", - "95446dc9a4cc46469d1efa27c7896bfc", - "3cd2ea08c82e49a08396e31dfead7f6f" - ] + "f16031daae714a0181ddd0b31471f060": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_82d5d05b953042f4bc7ad53a122d6a03", + "placeholder": "​", + "style": "IPY_MODEL_786cb3e450de464fa04f9ed4fbe073e1", + "value": " 234/234 [00:00<00:00, 8.80kB/s]" + } }, - "id": "bos-fW6CHijQ", - "outputId": "ad9f4982-f54c-4faa-c710-f3f7df98d480" - }, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "af584652d0304a899e66314d61726323", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "config.json: 0%| | 0.00/2.11k [00:00" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "plt.figure()\n", - "plt.imshow(spectrogram.T)\n", - "plt.show()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "McG3EnpYRJVj" - }, - "source": [ - "Finally, use the vocoder to turn the spectrogram into sound." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "MpogdOe_7uoe" - }, - "outputs": [], - "source": [ - "with torch.no_grad():\n", - " speech = vocoder(spectrogram)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 75 - }, - "id": "5H_FaVuW7wXt", - "outputId": "ce585e70-1e90-4cf5-af17-9ac311dee7ee" - }, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - " \n", - " " - ], - "text/plain": [ - "" - ] - }, - "execution_count": 61, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "from IPython.display import Audio\n", - "Audio(speech.numpy(), rate=16000)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 183 - }, - "id": "PV0nUOmO7xvv", - "outputId": "3e0c913d-86ac-41e6-dba1-144238fa147d" - }, - "outputs": [ - { - "ename": "TypeError", - "evalue": "can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msoundfile\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0msf\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0msf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"output.wav\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mspeech\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnumpy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msamplerate\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m16000\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[0;31mTypeError\u001b[0m: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first." - ] - } - ], - "source": [ - "import soundfile as sf\n", - "sf.write(\"output.wav\", speech.numpy(), samplerate=16000)" - ] - } - ], - "metadata": { - "accelerator": "GPU", - "colab": { - "gpuType": "T4", - "provenance": [] - }, - "kernelspec": { - "display_name": "Python 3", - "name": "python3" - }, - "language_info": { - "name": "python" - }, - "widgets": { - "application/vnd.jupyter.widget-state+json": { - "00adec96a5654f3a9d08c8331366f704": { + "1eabe7caf021425a83295181e16a573d": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3002,68 +1642,26 @@ "width": null } }, - "0194367f515647b1ae5bc638d212c2ce": { + "e281d772babb4a2dbb1a949e6a5a440c": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", + "bar_color": null, "description_width": "" } }, - "01a46b988d1347d7ba1cba3670ebed23": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_df0da2ae6ac6428aac6b61752c52bcc7", - "IPY_MODEL_d6f7f58dd281478483d66e9d42dd8d9e", - "IPY_MODEL_e114b6684c174e6ab2d71cfec2a8979e" - ], - "layout": "IPY_MODEL_fd58a16ab3b74680b5cec3c49a834793" - } - }, - "01e97533b18e4dd48d07a993c8e44b1f": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_252843c3c20f4c9f9327a6bec256db60", - "placeholder": "​", - "style": "IPY_MODEL_0f526d71ed8f480da0f258d1282e3042", - "value": "Map: 100%" - } - }, - "02948c857fb14040a5abbba1dc463bea": { + "82d5d05b953042f4bc7ad53a122d6a03": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3112,10 +1710,113 @@ "width": null } }, - "02e1add81ac742e7bfdcdb4f54069978": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", + "786cb3e450de464fa04f9ed4fbe073e1": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "6c036b53916642e3993b40b66532f305": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_f02b5874bc1a4b29a0a8f65a455ae425", + "IPY_MODEL_73bbb254a9f94a2f90776da888b551c2", + "IPY_MODEL_4b400af9107d4cb09725a19a8978d33a" + ], + "layout": "IPY_MODEL_decda57cc9a7489fb32d384c270f4994" + } + }, + "f02b5874bc1a4b29a0a8f65a455ae425": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_9b62f1cf2fe54ccda160abe4a281ca82", + "placeholder": "​", + "style": "IPY_MODEL_1073b875d7e040d1b96adc59ac722133", + "value": "config.json: 100%" + } + }, + "73bbb254a9f94a2f90776da888b551c2": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_22f2f7b6cad948efa54f0c748d427777", + "max": 2062, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_ba3d74aab1d44f44a3b795f4e4a9177e", + "value": 2062 + } + }, + "4b400af9107d4cb09725a19a8978d33a": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_0a6f959beecf45f4ba2d1cb19f21a3bc", + "placeholder": "​", + "style": "IPY_MODEL_efd7335a34584dcab1c2ece372c23332", + "value": " 2.06k/2.06k [00:00<00:00, 90.0kB/s]" + } + }, + "decda57cc9a7489fb32d384c270f4994": { + "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3164,10 +1865,10 @@ "width": null } }, - "032537b0ad9a4058879b8f3b2b2eb384": { + "9b62f1cf2fe54ccda160abe4a281ca82": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3216,77 +1917,10 @@ "width": null } }, - "032cf630889f4f599dad2a0f718dd63e": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "034918f3b833496397f34caa9a0bfbb4": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "04512216d85b42c4ae02d3f1083acbe9": { + "1073b875d7e040d1b96adc59ac722133": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "054b003700514935960c7ee0895b8c8e": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_2dcbcbfcbb3c455a8beee0d7f4c12c05", - "IPY_MODEL_be44a4398328449daebb6bd48e2519f7", - "IPY_MODEL_bcd4e9d178c944f6973b2d62fa1e5538" - ], - "layout": "IPY_MODEL_d8419ef35db5403c862e8321572ad376" - } - }, - "06508d700e9c426b85f374381d3439d9": { - "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -3298,10 +1932,10 @@ "description_width": "" } }, - "078823ec9ed64a58abc1ee0a7d55976a": { + "22f2f7b6cad948efa54f0c748d427777": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3350,10 +1984,26 @@ "width": null } }, - "08a04116a15043e88c1c50b76bc3a77b": { + "ba3d74aab1d44f44a3b795f4e4a9177e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "0a6f959beecf45f4ba2d1cb19f21a3bc": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3402,34 +2052,10 @@ "width": null } }, - "08cbe5b1b931421c8feb029485a4b122": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_b5cc29850b5a4fcfb3cd368d35081736", - "max": 260140503, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_4e45155fee7c499c94346155cb9430e4", - "value": 260140503 - } - }, - "0900daeba5cf4cb29d00a9c5ed5ad330": { + "efd7335a34584dcab1c2ece372c23332": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -3441,10 +2067,10 @@ "description_width": "" } }, - "09aa1693c138490db1fcb29f3d049a86": { + "f093bd48a659437692d44be6308d0a53": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HBoxModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -3456,23 +2082,89 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_c1052b9d43984c67b28c50c2a9d620a3", - "IPY_MODEL_555b7051e6bc4efdb35285300321748e", - "IPY_MODEL_793b16cd7280425faa37ba7bf19e16c0" + "IPY_MODEL_140712a8dbb04cdd8dd7854cc1b579e5", + "IPY_MODEL_980d09ee15b540a0868ed5e1cae7d867", + "IPY_MODEL_616095ba34964997a82d5103681ec8fd" ], - "layout": "IPY_MODEL_c3e26506549144279b7b60c3382b4486" + "layout": "IPY_MODEL_6d8d46c27f5e4d23a9170c06fb8e6947" } }, - "0a595220c4004b6ca316c47babe4e5a7": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", + "140712a8dbb04cdd8dd7854cc1b579e5": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_1715e69a4fb84798b1d8d081991d0e65", + "placeholder": "​", + "style": "IPY_MODEL_bb212e00ea9b416db52167e0a64608ee", + "value": "pytorch_model.bin: 100%" + } + }, + "980d09ee15b540a0868ed5e1cae7d867": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_304787fbe0984b9f887fc948a8b888fc", + "max": 585476837, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_e4138b99226846e9b4cfc4ea075329cd", + "value": 585476837 + } + }, + "616095ba34964997a82d5103681ec8fd": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f969b09762794b8f99ad8e2121945bc4", + "placeholder": "​", + "style": "IPY_MODEL_5348d94bb7114057bd7b3cb9885a0041", + "value": " 585M/585M [00:01<00:00, 293MB/s]" + } + }, + "6d8d46c27f5e4d23a9170c06fb8e6947": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, @@ -3515,10 +2207,10 @@ "width": null } }, - "0a6f959beecf45f4ba2d1cb19f21a3bc": { + "1715e69a4fb84798b1d8d081991d0e65": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3567,67 +2259,10 @@ "width": null } }, - "0ba493d747144e1daac6252c6accc886": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_9ecef1d0b473411b914eed7fa043478e", - "placeholder": "​", - "style": "IPY_MODEL_d827d96e5328476c80a212fad5570c78", - "value": "added_tokens.json: 100%" - } - }, - "0f526d71ed8f480da0f258d1282e3042": { + "bb212e00ea9b416db52167e0a64608ee": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "10545f9c4b774b8f9bd9ddc7ea140a39": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_8306a7f425464783b14fd397b5a4be33", - "placeholder": "​", - "style": "IPY_MODEL_b2612a5852164e98bc46b7242bf4ff4d", - "value": " 4112/4112 [00:01<00:00, 2142.66 examples/s]" - } - }, - "1073b875d7e040d1b96adc59ac722133": { - "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -3639,10 +2274,10 @@ "description_width": "" } }, - "10aea82371aa4b23bb1e2f906778f92e": { + "304787fbe0984b9f887fc948a8b888fc": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3691,10 +2326,26 @@ "width": null } }, - "115279124c584e2daa48346a7c9c8e9c": { + "e4138b99226846e9b4cfc4ea075329cd": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "f969b09762794b8f99ad8e2121945bc4": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3743,10 +2394,10 @@ "width": null } }, - "11d479256d314d3eab585386482e318b": { + "5348d94bb7114057bd7b3cb9885a0041": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -3758,40 +2409,98 @@ "description_width": "" } }, - "124894a722344b689aa9ef66ee1a96ca": { + "47168eafb8684feab256de9dd23345d7": { "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "HBoxModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_3915b0dd32b04572ab06a3aee2406aed", + "IPY_MODEL_17c1635424a6492293111ad8f5724af1", + "IPY_MODEL_1dad34a32d26450bb0ce5737a7f5f672" + ], + "layout": "IPY_MODEL_e538e8c2cb5c486e9019672e77926db4" } }, - "12a3c5f709d14b7c8d9fa62fa213b68d": { + "3915b0dd32b04572ab06a3aee2406aed": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "HTMLModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_131d82361e8c49e9992b09276a44df38", + "placeholder": "​", + "style": "IPY_MODEL_6b6750add1a84570ad5d064b511d7017", + "value": "Downloading metadata: 100%" } }, - "131d82361e8c49e9992b09276a44df38": { + "17c1635424a6492293111ad8f5724af1": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_789066d9a9e04bc7b34da287dae1ad14", + "max": 1151, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_efedd4a0d92a4a9497276de827370261", + "value": 1151 + } + }, + "1dad34a32d26450bb0ce5737a7f5f672": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_02948c857fb14040a5abbba1dc463bea", + "placeholder": "​", + "style": "IPY_MODEL_71cc5fea590e4eaa813a4b18ffcf2a19", + "value": " 1.15k/1.15k [00:00<00:00, 80.2kB/s]" + } + }, + "e538e8c2cb5c486e9019672e77926db4": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3840,10 +2549,10 @@ "width": null } }, - "13226fa6805041fdb7e3976e4577a66e": { + "131d82361e8c49e9992b09276a44df38": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3892,10 +2601,25 @@ "width": null } }, - "1395fd0ce48b444c89915febefec9e96": { + "6b6750add1a84570ad5d064b511d7017": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "789066d9a9e04bc7b34da287dae1ad14": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -3944,31 +2668,26 @@ "width": null } }, - "140712a8dbb04cdd8dd7854cc1b579e5": { + "efedd4a0d92a4a9497276de827370261": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "ProgressStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_1715e69a4fb84798b1d8d081991d0e65", - "placeholder": "​", - "style": "IPY_MODEL_bb212e00ea9b416db52167e0a64608ee", - "value": "pytorch_model.bin: 100%" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" } }, - "156fa699696c4e26b2842e89954d202b": { + "02948c857fb14040a5abbba1dc463bea": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -4017,10 +2736,10 @@ "width": null } }, - "1660e3387e094116b87f3a8f04782124": { + "71cc5fea590e4eaa813a4b18ffcf2a19": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -4032,102 +2751,53 @@ "description_width": "" } }, - "16951d20b1294e08b42339d08f97ae7b": { + "9e64b696d550460792e4829c6ebd5342": { "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "HBoxModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_6a540a4e656b4286aa5135fc4ea66ece", + "IPY_MODEL_08cbe5b1b931421c8feb029485a4b122", + "IPY_MODEL_28052ac1a482483fb430936be0848b38" + ], + "layout": "IPY_MODEL_703e99ef518b4f40b1936147ce8d542d" } }, - "169d1b4d3773401688dc1884d6532788": { + "6a540a4e656b4286aa5135fc4ea66ece": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", + "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_fec3ab0d0be74c40a868ca3969e533c5", - "max": 232, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_16951d20b1294e08b42339d08f97ae7b", - "value": 232 - } - }, - "1715e69a4fb84798b1d8d081991d0e65": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null + "layout": "IPY_MODEL_032537b0ad9a4058879b8f3b2b2eb384", + "placeholder": "​", + "style": "IPY_MODEL_124894a722344b689aa9ef66ee1a96ca", + "value": "Downloading data: 100%" } }, - "17c1635424a6492293111ad8f5724af1": { + "08cbe5b1b931421c8feb029485a4b122": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -4140,40 +2810,39 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_789066d9a9e04bc7b34da287dae1ad14", - "max": 1151, + "layout": "IPY_MODEL_b5cc29850b5a4fcfb3cd368d35081736", + "max": 260140503, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_efedd4a0d92a4a9497276de827370261", - "value": 1151 + "style": "IPY_MODEL_4e45155fee7c499c94346155cb9430e4", + "value": 260140503 } }, - "17f05d9f756e466eba646e8dca6a89e3": { + "28052ac1a482483fb430936be0848b38": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "ButtonModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ButtonModel", + "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "ButtonView", - "button_style": "", - "description": "Login", - "disabled": false, - "icon": "", - "layout": "IPY_MODEL_0a595220c4004b6ca316c47babe4e5a7", - "style": "IPY_MODEL_1e34bc54a39b42b1a5a2ece20823ca3f", - "tooltip": "" + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_02e1add81ac742e7bfdcdb4f54069978", + "placeholder": "​", + "style": "IPY_MODEL_2334f26430754df990a9dccf1b51c214", + "value": " 260M/260M [00:01<00:00, 208MB/s]" } }, - "18f235d673c1422abc9a7a897295aaf4": { + "703e99ef518b4f40b1936147ce8d542d": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -4222,10 +2891,10 @@ "width": null } }, - "1a7fc55d69f448ada5d8ff2834a299ee": { + "032537b0ad9a4058879b8f3b2b2eb384": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -4274,53 +2943,10 @@ "width": null } }, - "1c0c9d45f86f4945965a4784109020ff": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_8462433da1b847b09f137a5017b575c8", - "IPY_MODEL_6535f9ad0436497dbcec30c1df342ac9", - "IPY_MODEL_4d02d845fa034829900635be82eb64ad" - ], - "layout": "IPY_MODEL_6d274c81d3ed486a90598cee551db717" - } - }, - "1dad34a32d26450bb0ce5737a7f5f672": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_02948c857fb14040a5abbba1dc463bea", - "placeholder": "​", - "style": "IPY_MODEL_71cc5fea590e4eaa813a4b18ffcf2a19", - "value": " 1.15k/1.15k [00:00<00:00, 80.2kB/s]" - } - }, - "1e1213f764474d7bbd426a5327829eb9": { + "124894a722344b689aa9ef66ee1a96ca": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -4332,26 +2958,10 @@ "description_width": "" } }, - "1e34bc54a39b42b1a5a2ece20823ca3f": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ButtonStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ButtonStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "button_color": null, - "font_weight": "" - } - }, - "1eabe7caf021425a83295181e16a573d": { + "b5cc29850b5a4fcfb3cd368d35081736": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -4400,31 +3010,93 @@ "width": null } }, - "1f15ee66a1f24e41b5630d5616243a7b": { + "4e45155fee7c499c94346155cb9430e4": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "ProgressStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_db9886b3bdf24a7690e5464275656dca", - "placeholder": "​", - "style": "IPY_MODEL_5c7aa125de6544cf9ff580cceb311c9e", - "value": "hyperparams.yaml: 100%" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" } }, - "1fff9026fa29474ca2b652a2e0e98235": { + "02e1add81ac742e7bfdcdb4f54069978": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "2334f26430754df990a9dccf1b51c214": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "2758d263bbab4816bd2b568e00168b59": { + "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -4436,17 +3108,83 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_eebdffbf80d542a0bdea7e2e4f66fbe8", - "IPY_MODEL_7827a86376c94da99efb90f5842864ed", - "IPY_MODEL_d8c83b57302a458aa3ee71cac9632455" + "IPY_MODEL_343f4701b1584ca297dba4328e59f135", + "IPY_MODEL_aa43ed4fb93c4089b5a9e64cb6adb9f3", + "IPY_MODEL_6799f03fc773436a9ff7f8b1157b0885" ], - "layout": "IPY_MODEL_08a04116a15043e88c1c50b76bc3a77b" + "layout": "IPY_MODEL_1395fd0ce48b444c89915febefec9e96" } }, - "22f2f7b6cad948efa54f0c748d427777": { + "343f4701b1584ca297dba4328e59f135": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_c8e59f437cc74c4da6fbdab1f69630dd", + "placeholder": "​", + "style": "IPY_MODEL_7569d59db923484399859632e3bcac12", + "value": "Downloading data: 100%" + } + }, + "aa43ed4fb93c4089b5a9e64cb6adb9f3": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b821ee6883804da09ca3c35c510dd8da", + "max": 255659282, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_596d960afbb24861a220d63745b271a6", + "value": 255659282 + } + }, + "6799f03fc773436a9ff7f8b1157b0885": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_411391536a254ccfa5f57cb824b0d54c", + "placeholder": "​", + "style": "IPY_MODEL_a33b6fea82cb4c31a00bc7da57837fa3", + "value": " 256M/256M [00:03<00:00, 278MB/s]" + } + }, + "1395fd0ce48b444c89915febefec9e96": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -4495,10 +3233,10 @@ "width": null } }, - "22f4b0480fd34920b9a2e0c9d8c609dc": { + "c8e59f437cc74c4da6fbdab1f69630dd": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -4547,10 +3285,10 @@ "width": null } }, - "2334f26430754df990a9dccf1b51c214": { + "7569d59db923484399859632e3bcac12": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -4562,10 +3300,10 @@ "description_width": "" } }, - "252843c3c20f4c9f9327a6bec256db60": { + "b821ee6883804da09ca3c35c510dd8da": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -4614,84 +3352,93 @@ "width": null } }, - "265bbe545b99430f85aa5884b64ac014": { + "596d960afbb24861a220d63745b271a6": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", + "bar_color": null, "description_width": "" } }, - "2758d263bbab4816bd2b568e00168b59": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", + "411391536a254ccfa5f57cb824b0d54c": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_343f4701b1584ca297dba4328e59f135", - "IPY_MODEL_aa43ed4fb93c4089b5a9e64cb6adb9f3", - "IPY_MODEL_6799f03fc773436a9ff7f8b1157b0885" - ], - "layout": "IPY_MODEL_1395fd0ce48b444c89915febefec9e96" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null } }, - "27b0e9d94b0a4d8cac920df223606d10": { + "a33b6fea82cb4c31a00bc7da57837fa3": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", - "bar_color": null, "description_width": "" } }, - "28052ac1a482483fb430936be0848b38": { + "01a46b988d1347d7ba1cba3670ebed23": { "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_02e1add81ac742e7bfdcdb4f54069978", - "placeholder": "​", - "style": "IPY_MODEL_2334f26430754df990a9dccf1b51c214", - "value": " 260M/260M [00:01<00:00, 208MB/s]" - } - }, - "2993094c7ff6425eab9bb0b1bdf1d7ac": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -4703,33 +3450,17 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_fd6cb6748b1a4d83bbd3c1f9bc9293c9", - "IPY_MODEL_a15ad78eb7e249a2ae8f1a4e0b0e359e", - "IPY_MODEL_39f6a7a3035a4c53bebc34e7a90ad14c" + "IPY_MODEL_df0da2ae6ac6428aac6b61752c52bcc7", + "IPY_MODEL_d6f7f58dd281478483d66e9d42dd8d9e", + "IPY_MODEL_e114b6684c174e6ab2d71cfec2a8979e" ], - "layout": "IPY_MODEL_078823ec9ed64a58abc1ee0a7d55976a" - } - }, - "2c9002098b114841b511b97c5fa39f14": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" + "layout": "IPY_MODEL_fd58a16ab3b74680b5cec3c49a834793" } }, - "2d3eb78c7b994f3cb2d57d80458c35d6": { + "df0da2ae6ac6428aac6b61752c52bcc7": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -4741,59 +3472,61 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_5d30def7a2bb463baa858eb0eee9d094", + "layout": "IPY_MODEL_69ee5b1b8e864d8180913e5ab758b630", "placeholder": "​", - "style": "IPY_MODEL_06508d700e9c426b85f374381d3439d9", - "value": "pytorch_model.bin: 100%" + "style": "IPY_MODEL_6f667950dd5d48c5bd693d52494bfee3", + "value": "Downloading data: 100%" } }, - "2dcbcbfcbb3c455a8beee0d7f4c12c05": { + "d6f7f58dd281478483d66e9d42dd8d9e": { "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HTMLView", + "_view_name": "ProgressView", + "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_af01cdbb16dd490984a749d2da6eff34", - "placeholder": "​", - "style": "IPY_MODEL_54783e715ad0408eaa512f7d28a374b2", - "value": "model.safetensors: 100%" + "layout": "IPY_MODEL_4cbded0a06734d1b9df19c952e13f08a", + "max": 113869079, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_4664dcf8fe2945978d5033f996ae5e10", + "value": 113869079 } }, - "2ebee62340c24076b6edeb96d233b5e0": { + "e114b6684c174e6ab2d71cfec2a8979e": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_dc0e721504184b778486802d47239e00", - "IPY_MODEL_4744d62b21e645b8bad84578aed387d3", - "IPY_MODEL_ef635c73df96463ea145fad659b04028" - ], - "layout": "IPY_MODEL_00adec96a5654f3a9d08c8331366f704" + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4ef8777ca3d44098b37bbacb941be225", + "placeholder": "​", + "style": "IPY_MODEL_64de190bb8954e6e81698876ec06e9c6", + "value": " 114M/114M [00:00<00:00, 263MB/s]" } }, - "304787fbe0984b9f887fc948a8b888fc": { + "fd58a16ab3b74680b5cec3c49a834793": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -4842,10 +3575,10 @@ "width": null } }, - "308b5dd72e6f4ea39d9be4c2e4a02512": { + "69ee5b1b8e864d8180913e5ab758b630": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -4894,163 +3627,25 @@ "width": null } }, - "3109d5c2ffe04d5ebf296cc26a334a38": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_c1b4ea7cfc0d434dbb68027af48a5f07", - "placeholder": "​", - "style": "IPY_MODEL_5e1fd59b51d1459da614ab5d51116d59", - "value": "generation_config.json: 100%" - } - }, - "31ed87b6e80b4822b430c51ae043edcf": { + "6f667950dd5d48c5bd693d52494bfee3": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "33e739de4df54f96a276027d2d1f66ea": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_2d3eb78c7b994f3cb2d57d80458c35d6", - "IPY_MODEL_de8ee1e97a0f4bbfa17281a0c067b5b1", - "IPY_MODEL_5ab5b7305633479494e991c26c2268a9" - ], - "layout": "IPY_MODEL_ab27bce16ed24effbddb7596ffe2c3c1" - } - }, - "343f4701b1584ca297dba4328e59f135": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_c8e59f437cc74c4da6fbdab1f69630dd", - "placeholder": "​", - "style": "IPY_MODEL_7569d59db923484399859632e3bcac12", - "value": "Downloading data: 100%" - } - }, - "346edbb27fec4479ad74331561fe6d4f": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "LabelModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "LabelModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "LabelView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_5942dd51d8014d32a6400698fa84f88e", - "placeholder": "​", - "style": "IPY_MODEL_813e7e5696b84a0091524b551d94b1a6", - "value": "Token is valid (permission: write)." - } - }, - "350f730b810f4bd88740a77a7e0a51be": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "3518110403534f7f82a617d1bedc6315": { - "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", - "bar_color": null, "description_width": "" } }, - "37034519aba0437a89c974c344cc58be": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_c8be0944b2d14e47a2f7909138527aaf", - "placeholder": "​", - "style": "IPY_MODEL_11d479256d314d3eab585386482e318b", - "value": "preprocessor_config.json: 100%" - } - }, - "37f6208a83084b92a458e21c197cad3f": { + "4cbded0a06734d1b9df19c952e13f08a": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -5099,53 +3694,26 @@ "width": null } }, - "382582721b924a77a6ed9ebf2d0e78c6": { + "4664dcf8fe2945978d5033f996ae5e10": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "LabelModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "LabelModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "LabelView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_59f995c679f843eba17be9f2cab2b5ca", - "placeholder": "​", - "style": "IPY_MODEL_aa7bf7b3cc7441888151beffb6d30321", - "value": "Your token has been saved in your configured git credential helpers (store)." - } - }, - "3883ac03bf194a0593df865f3fe7f4bc": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "ProgressStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_01e97533b18e4dd48d07a993c8e44b1f", - "IPY_MODEL_db2c1cf6f56c4aefa44e2da5b1b85a67", - "IPY_MODEL_10545f9c4b774b8f9bd9ddc7ea140a39" - ], - "layout": "IPY_MODEL_afecd676c8024a89bc20165215fc7f5c" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" } }, - "3915aa47172546afb3f09ea1f7c5b947": { + "4ef8777ca3d44098b37bbacb941be225": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -5194,31 +3762,47 @@ "width": null } }, - "3915b0dd32b04572ab06a3aee2406aed": { + "64de190bb8954e6e81698876ec06e9c6": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "8c4bc267343547898e5daf05dfc1b244": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_131d82361e8c49e9992b09276a44df38", - "placeholder": "​", - "style": "IPY_MODEL_6b6750add1a84570ad5d064b511d7017", - "value": "Downloading metadata: 100%" + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_f511ee45542b4bc3be2009a8ff76b319", + "IPY_MODEL_b0a23f6a0e0641269686214f25829ffd", + "IPY_MODEL_3d4aed875264486187bc9ccb18881eb8" + ], + "layout": "IPY_MODEL_6e721aa59b9c4104b5eb823feacc4f42" } }, - "39f6a7a3035a4c53bebc34e7a90ad14c": { + "f511ee45542b4bc3be2009a8ff76b319": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -5230,32 +3814,40 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_c350945401cb48968758c0674598a855", + "layout": "IPY_MODEL_1a7fc55d69f448ada5d8ff2834a299ee", "placeholder": "​", - "style": "IPY_MODEL_0194367f515647b1ae5bc638d212c2ce", - "value": " 4112/4112 [00:00<00:00, 38198.02 examples/s]" + "style": "IPY_MODEL_12a3c5f709d14b7c8d9fa62fa213b68d", + "value": "Generating train split: 100%" } }, - "3b0b3cb12bd34d2c8898a1bc0a938c4c": { + "b0a23f6a0e0641269686214f25829ffd": { "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "FloatProgressModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_3d0c025d4bab42f1b53a808aeb9ba942", + "max": 4112, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_3b0b3cb12bd34d2c8898a1bc0a938c4c", + "value": 4112 } }, - "3b74fdd0043949548e50b1d87413505b": { + "3d4aed875264486187bc9ccb18881eb8": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -5267,16 +3859,16 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_6916935a59f94d6e95449be55732c80c", + "layout": "IPY_MODEL_8d117be740ff40b8b5bb62db6f0e8c79", "placeholder": "​", - "style": "IPY_MODEL_cef8c2e1224b4f0eb21e4963d53431b5", - "value": "config.json: 100%" + "style": "IPY_MODEL_a06f4c8a4ca544339eebffd9cbacb32e", + "value": " 4112/4112 [00:03<00:00, 1215.97 examples/s]" } }, - "3bd4aa82001248acb3758f0ff98fe64c": { + "6e721aa59b9c4104b5eb823feacc4f42": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -5325,25 +3917,10 @@ "width": null } }, - "3cd2ea08c82e49a08396e31dfead7f6f": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "3d0c025d4bab42f1b53a808aeb9ba942": { + "1a7fc55d69f448ada5d8ff2834a299ee": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -5392,31 +3969,25 @@ "width": null } }, - "3d4aed875264486187bc9ccb18881eb8": { + "12a3c5f709d14b7c8d9fa62fa213b68d": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_8d117be740ff40b8b5bb62db6f0e8c79", - "placeholder": "​", - "style": "IPY_MODEL_a06f4c8a4ca544339eebffd9cbacb32e", - "value": " 4112/4112 [00:03<00:00, 1215.97 examples/s]" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" } }, - "3e0e63681dfe4201ae9d8b7a370fca52": { + "3d0c025d4bab42f1b53a808aeb9ba942": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -5465,10 +4036,10 @@ "width": null } }, - "3f9e48a1f9014418825baa991e0f422c": { + "3b0b3cb12bd34d2c8898a1bc0a938c4c": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -5481,25 +4052,10 @@ "description_width": "" } }, - "3fb43042ede944c485c1eadf21ebfa96": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "3fd3b45e98ff4292a1444f89fc6ae95e": { + "8d117be740ff40b8b5bb62db6f0e8c79": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -5548,139 +4104,113 @@ "width": null } }, - "411391536a254ccfa5f57cb824b0d54c": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", + "a06f4c8a4ca544339eebffd9cbacb32e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null + "_view_name": "StyleView", + "description_width": "" } }, - "4138156fdfcf4d41947457d9670425df": { + "09aa1693c138490db1fcb29f3d049a86": { "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_22f4b0480fd34920b9a2e0c9d8c609dc", - "max": 40, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_3f9e48a1f9014418825baa991e0f422c", - "value": 40 + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_c1052b9d43984c67b28c50c2a9d620a3", + "IPY_MODEL_555b7051e6bc4efdb35285300321748e", + "IPY_MODEL_793b16cd7280425faa37ba7bf19e16c0" + ], + "layout": "IPY_MODEL_c3e26506549144279b7b60c3382b4486" } }, - "456aa13fa38c4c01b9f43570e31556fe": { + "c1052b9d43984c67b28c50c2a9d620a3": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_ec7ac27d32c44b40ac8fd18a7700962d", - "IPY_MODEL_fbeb5a0f2394434fb67644f452dcb6b2", - "IPY_MODEL_f22ab8b84c9a406d9383a1253576cf62" - ], - "layout": "IPY_MODEL_3915aa47172546afb3f09ea1f7c5b947" + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7e7bb5871ded4f57ad44fb9e17116be1", + "placeholder": "​", + "style": "IPY_MODEL_b029a4f4c27340808012eab6ba5573ed", + "value": "Generating test split: 100%" } }, - "45e7d7b493fb45d1b71b0f42464a9ac8": { + "555b7051e6bc4efdb35285300321748e": { "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "FloatProgressModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_d00a6c69c91747ee952a78cabb4b5f73", + "max": 1000, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_575e3e858d734fb08d2072944aa57a15", + "value": 1000 } }, - "4664dcf8fe2945978d5033f996ae5e10": { + "793b16cd7280425faa37ba7bf19e16c0": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "HTMLModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4ee7e82441c74fc9b726d996a49c6908", + "placeholder": "​", + "style": "IPY_MODEL_cc1c35d92b754ff29989ecc023bb9e25", + "value": " 1000/1000 [00:00<00:00, 2329.73 examples/s]" } }, - "4699dc096aa644b6add210252efa7334": { + "c3e26506549144279b7b60c3382b4486": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -5729,87 +4259,10 @@ "width": null } }, - "47168eafb8684feab256de9dd23345d7": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_3915b0dd32b04572ab06a3aee2406aed", - "IPY_MODEL_17c1635424a6492293111ad8f5724af1", - "IPY_MODEL_1dad34a32d26450bb0ce5737a7f5f672" - ], - "layout": "IPY_MODEL_e538e8c2cb5c486e9019672e77926db4" - } - }, - "4744d62b21e645b8bad84578aed387d3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_4699dc096aa644b6add210252efa7334", - "max": 4112, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_f2f329976e13413c9bcef0e56280d563", - "value": 4112 - } - }, - "494b73ce426e44da9601305d859f484c": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "499ae3562b0e4636a5526230245d502a": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "4a7bd718c8874fc2bbd7a566e1da124d": { + "7e7bb5871ded4f57ad44fb9e17116be1": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -5858,10 +4311,10 @@ "width": null } }, - "4acb801fd07e4e1db048921d83fad83f": { + "b029a4f4c27340808012eab6ba5573ed": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -5873,76 +4326,10 @@ "description_width": "" } }, - "4b400af9107d4cb09725a19a8978d33a": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_0a6f959beecf45f4ba2d1cb19f21a3bc", - "placeholder": "​", - "style": "IPY_MODEL_efd7335a34584dcab1c2ece372c23332", - "value": " 2.06k/2.06k [00:00<00:00, 90.0kB/s]" - } - }, - "4bdb55d30a0b4b648c082f2cf5921383": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_c4660f3058d14daba1940d89e200b65d", - "placeholder": "​", - "style": "IPY_MODEL_31ed87b6e80b4822b430c51ae043edcf", - "value": "


Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
" - } - }, - "4ca762251949444f921863535a18e5c5": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_4a7bd718c8874fc2bbd7a566e1da124d", - "max": 636, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_ea8fbaa445bd442b82bb60a67b0efcea", - "value": 636 - } - }, - "4cbded0a06734d1b9df19c952e13f08a": { + "d00a6c69c91747ee952a78cabb4b5f73": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -5991,31 +4378,26 @@ "width": null } }, - "4d02d845fa034829900635be82eb64ad": { + "575e3e858d734fb08d2072944aa57a15": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "ProgressStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_a10a271823244bce91dbc042bf838746", - "placeholder": "​", - "style": "IPY_MODEL_265bbe545b99430f85aa5884b64ac014", - "value": " 129k/129k [00:00<00:00, 3.88MB/s]" - } - }, - "4d5bdff9982e40138888bc9c72f9233e": { + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "4ee7e82441c74fc9b726d996a49c6908": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -6064,10 +4446,68 @@ "width": null } }, - "4d97d63c12ab4c37b53207cf91ac9794": { + "cc1c35d92b754ff29989ecc023bb9e25": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "3883ac03bf194a0593df865f3fe7f4bc": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_01e97533b18e4dd48d07a993c8e44b1f", + "IPY_MODEL_db2c1cf6f56c4aefa44e2da5b1b85a67", + "IPY_MODEL_10545f9c4b774b8f9bd9ddc7ea140a39" + ], + "layout": "IPY_MODEL_afecd676c8024a89bc20165215fc7f5c" + } + }, + "01e97533b18e4dd48d07a993c8e44b1f": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_252843c3c20f4c9f9327a6bec256db60", + "placeholder": "​", + "style": "IPY_MODEL_0f526d71ed8f480da0f258d1282e3042", + "value": "Map: 100%" + } + }, + "db2c1cf6f56c4aefa44e2da5b1b85a67": { + "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -6080,34 +4520,39 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ced524c3f07b40e792db0bf1e9c3fe92", - "max": 190, + "layout": "IPY_MODEL_82287f32ca37416b824ac2dcef8adcc1", + "max": 4112, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_b257195cf3314cb4bc3aeddc4da142b9", - "value": 190 + "style": "IPY_MODEL_e376e343655744e0b09f3fe3212c1d41", + "value": 4112 } }, - "4e45155fee7c499c94346155cb9430e4": { + "10545f9c4b774b8f9bd9ddc7ea140a39": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "HTMLModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_8306a7f425464783b14fd397b5a4be33", + "placeholder": "​", + "style": "IPY_MODEL_b2612a5852164e98bc46b7242bf4ff4d", + "value": " 4112/4112 [00:01<00:00, 2142.66 examples/s]" } }, - "4edcc714fca4485190e973ed83325af1": { + "afecd676c8024a89bc20165215fc7f5c": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -6156,10 +4601,10 @@ "width": null } }, - "4ee7e82441c74fc9b726d996a49c6908": { + "252843c3c20f4c9f9327a6bec256db60": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -6208,10 +4653,25 @@ "width": null } }, - "4ef8777ca3d44098b37bbacb941be225": { + "0f526d71ed8f480da0f258d1282e3042": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "82287f32ca37416b824ac2dcef8adcc1": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -6260,107 +4720,10 @@ "width": null } }, - "506636dde3f4495fa929c659ecf8b764": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_c16b239971bc41d8be09280b34536fd4", - "placeholder": "​", - "style": "IPY_MODEL_e92855e89e3e4ebba0159c6f24004aad", - "value": " 433/433 [00:00<00:00, 32.7kB/s]" - } - }, - "5348d94bb7114057bd7b3cb9885a0041": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "54783e715ad0408eaa512f7d28a374b2": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "5492a2c2d56844bdabc9aaaab9bdc35f": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_669272db738947e2b8102102a57bc87a", - "IPY_MODEL_dad194753c8e439c9d62285c0c06546a", - "IPY_MODEL_ae2f4d6301694356b5878fab0de3ea83" - ], - "layout": "IPY_MODEL_156fa699696c4e26b2842e89954d202b" - } - }, - "555b7051e6bc4efdb35285300321748e": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_d00a6c69c91747ee952a78cabb4b5f73", - "max": 1000, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_575e3e858d734fb08d2072944aa57a15", - "value": 1000 - } - }, - "575e3e858d734fb08d2072944aa57a15": { + "e376e343655744e0b09f3fe3212c1d41": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -6373,10 +4736,10 @@ "description_width": "" } }, - "5942dd51d8014d32a6400698fa84f88e": { + "8306a7f425464783b14fd397b5a4be33": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -6425,26 +4788,25 @@ "width": null } }, - "596d960afbb24861a220d63745b271a6": { + "b2612a5852164e98bc46b7242bf4ff4d": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", - "bar_color": null, "description_width": "" } }, - "59b8375db47b41709137a8831f06a693": { + "d8e8d1b0adcd4d47b061aad1486604cb": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HBoxModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -6456,18 +4818,84 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_969bec5ee95248d4a948965c74ff3311", - "IPY_MODEL_8f604dc7fccf4572821cb040ab5d8c5c", - "IPY_MODEL_677cfd9f2d3f4f669e488d12d21b8e20" + "IPY_MODEL_1f15ee66a1f24e41b5630d5616243a7b", + "IPY_MODEL_651b513c24e24a5990591f95f24a4c0a", + "IPY_MODEL_708e0de686af4966a72d66fb174c1cfa" ], - "layout": "IPY_MODEL_974b89e5205a4487acb8577df5ea85e6" + "layout": "IPY_MODEL_f46eb3dacc954c729a2c2b44d91a5382" } }, - "59f995c679f843eba17be9f2cab2b5ca": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { + "1f15ee66a1f24e41b5630d5616243a7b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_db9886b3bdf24a7690e5464275656dca", + "placeholder": "​", + "style": "IPY_MODEL_5c7aa125de6544cf9ff580cceb311c9e", + "value": "hyperparams.yaml: 100%" + } + }, + "651b513c24e24a5990591f95f24a4c0a": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f0297cf643064c4c97df2e0749207379", + "max": 2041, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_caaca6fb45eb453dbd2d8bb4ff5d3d52", + "value": 2041 + } + }, + "708e0de686af4966a72d66fb174c1cfa": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_c78ec4ad3bfb443982281085989394fe", + "placeholder": "​", + "style": "IPY_MODEL_032cf630889f4f599dad2a0f718dd63e", + "value": " 2.04k/2.04k [00:00<00:00, 79.2kB/s]" + } + }, + "f46eb3dacc954c729a2c2b44d91a5382": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", @@ -6515,68 +4943,10 @@ "width": null } }, - "5ab5b7305633479494e991c26c2268a9": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_e550d62c5fb54e8c9be548e252a4ddc3", - "placeholder": "​", - "style": "IPY_MODEL_b51084470848412d9360ed3487aaf3f6", - "value": " 50.7M/50.7M [00:00<00:00, 103MB/s]" - } - }, - "5c7aa125de6544cf9ff580cceb311c9e": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "5cd4197ba6cb43a79e8e48e3281d556a": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_37034519aba0437a89c974c344cc58be", - "IPY_MODEL_69a2281cd24c473fa2f4874034bfe1bd", - "IPY_MODEL_506636dde3f4495fa929c659ecf8b764" - ], - "layout": "IPY_MODEL_67fd8b2359ec4585a548b52f614531f1" - } - }, - "5d30def7a2bb463baa858eb0eee9d094": { + "db9886b3bdf24a7690e5464275656dca": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -6625,41 +4995,25 @@ "width": null } }, - "5e1fd59b51d1459da614ab5d51116d59": { + "5c7aa125de6544cf9ff580cceb311c9e": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "5f90e9766c3b44f0bded6715e12682d5": { - "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", - "bar_color": null, "description_width": "" } }, - "601c4fb9215444efb45f55852abd41d5": { + "f0297cf643064c4c97df2e0749207379": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -6708,10 +5062,10 @@ "width": null } }, - "6035b946f770456fbfd123adbb5e3be9": { + "caaca6fb45eb453dbd2d8bb4ff5d3d52": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -6724,83 +5078,10 @@ "description_width": "" } }, - "616095ba34964997a82d5103681ec8fd": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_f969b09762794b8f99ad8e2121945bc4", - "placeholder": "​", - "style": "IPY_MODEL_5348d94bb7114057bd7b3cb9885a0041", - "value": " 585M/585M [00:01<00:00, 293MB/s]" - } - }, - "630aa4eac24e481a9fdb9d999f0c8822": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "64917c2ed79841e3a5080ffbe11baba8": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_976a925fc43c42f1a580fd808d32023d", - "IPY_MODEL_9bf02a53411646439af4b7412d707923", - "IPY_MODEL_fadd75cae7824fa598fd58ae994259ab" - ], - "layout": "IPY_MODEL_d7cd149116154f98aad430d857c46381" - } - }, - "64de190bb8954e6e81698876ec06e9c6": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "64eb31cf8d59468ea56a8e58c71d8122": { + "c78ec4ad3bfb443982281085989394fe": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -6849,58 +5130,47 @@ "width": null } }, - "651b513c24e24a5990591f95f24a4c0a": { + "032cf630889f4f599dad2a0f718dd63e": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_f0297cf643064c4c97df2e0749207379", - "max": 2041, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_caaca6fb45eb453dbd2d8bb4ff5d3d52", - "value": 2041 + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" } }, - "6535f9ad0436497dbcec30c1df342ac9": { + "59b8375db47b41709137a8831f06a693": { "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_10aea82371aa4b23bb1e2f906778f92e", - "max": 128619, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_935177cdab4a419ebb327a9641c2a6ff", - "value": 128619 + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_969bec5ee95248d4a948965c74ff3311", + "IPY_MODEL_8f604dc7fccf4572821cb040ab5d8c5c", + "IPY_MODEL_677cfd9f2d3f4f669e488d12d21b8e20" + ], + "layout": "IPY_MODEL_974b89e5205a4487acb8577df5ea85e6" } }, - "669272db738947e2b8102102a57bc87a": { + "969bec5ee95248d4a948965c74ff3311": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -6912,37 +5182,40 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_b0cda3f2c228491bb6ce981267141f52", + "layout": "IPY_MODEL_3e0e63681dfe4201ae9d8b7a370fca52", "placeholder": "​", - "style": "IPY_MODEL_3fb43042ede944c485c1eadf21ebfa96", - "value": "classifier.ckpt: 100%" + "style": "IPY_MODEL_630aa4eac24e481a9fdb9d999f0c8822", + "value": "embedding_model.ckpt: 100%" } }, - "677cfd9f2d3f4f669e488d12d21b8e20": { + "8f604dc7fccf4572821cb040ab5d8c5c": { "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HTMLView", + "_view_name": "ProgressView", + "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_9d8b343299174f5789bfef21e23cfff6", - "placeholder": "​", - "style": "IPY_MODEL_8c299f76bb244a748838b967e5d93c2f", - "value": " 16.9M/16.9M [00:00<00:00, 90.0MB/s]" + "layout": "IPY_MODEL_6b988b31851c4db6890479404c7011cf", + "max": 16887676, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_27b0e9d94b0a4d8cac920df223606d10", + "value": 16887676 } }, - "6799f03fc773436a9ff7f8b1157b0885": { + "677cfd9f2d3f4f669e488d12d21b8e20": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -6954,16 +5227,16 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_411391536a254ccfa5f57cb824b0d54c", + "layout": "IPY_MODEL_9d8b343299174f5789bfef21e23cfff6", "placeholder": "​", - "style": "IPY_MODEL_a33b6fea82cb4c31a00bc7da57837fa3", - "value": " 256M/256M [00:03<00:00, 278MB/s]" + "style": "IPY_MODEL_8c299f76bb244a748838b967e5d93c2f", + "value": " 16.9M/16.9M [00:00<00:00, 90.0MB/s]" } }, - "67fd8b2359ec4585a548b52f614531f1": { + "974b89e5205a4487acb8577df5ea85e6": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7012,10 +5285,10 @@ "width": null } }, - "68a15f79b7ab42eaa0b14086f2b54ed6": { + "3e0e63681dfe4201ae9d8b7a370fca52": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7064,10 +5337,25 @@ "width": null } }, - "6916935a59f94d6e95449be55732c80c": { + "630aa4eac24e481a9fdb9d999f0c8822": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "6b988b31851c4db6890479404c7011cf": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7116,34 +5404,26 @@ "width": null } }, - "69a2281cd24c473fa2f4874034bfe1bd": { + "27b0e9d94b0a4d8cac920df223606d10": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "ProgressStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_115279124c584e2daa48346a7c9c8e9c", - "max": 433, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_350f730b810f4bd88740a77a7e0a51be", - "value": 433 + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" } }, - "69ee5b1b8e864d8180913e5ab758b630": { + "9d8b343299174f5789bfef21e23cfff6": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7192,10 +5472,47 @@ "width": null } }, - "6a540a4e656b4286aa5135fc4ea66ece": { + "8c299f76bb244a748838b967e5d93c2f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "1fff9026fa29474ca2b652a2e0e98235": { "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_eebdffbf80d542a0bdea7e2e4f66fbe8", + "IPY_MODEL_7827a86376c94da99efb90f5842864ed", + "IPY_MODEL_d8c83b57302a458aa3ee71cac9632455" + ], + "layout": "IPY_MODEL_08a04116a15043e88c1c50b76bc3a77b" + } + }, + "eebdffbf80d542a0bdea7e2e4f66fbe8": { + "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -7207,31 +5524,61 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_032537b0ad9a4058879b8f3b2b2eb384", + "layout": "IPY_MODEL_e1f400ffbb124a56a281832bcc54eaf9", "placeholder": "​", - "style": "IPY_MODEL_124894a722344b689aa9ef66ee1a96ca", - "value": "Downloading data: 100%" + "style": "IPY_MODEL_a3ef8ad842a346df9ffc0f31725c9606", + "value": "mean_var_norm_emb.ckpt: 100%" } }, - "6b6750add1a84570ad5d064b511d7017": { + "7827a86376c94da99efb90f5842864ed": { "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "FloatProgressModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_fa605877967d4109a4fd496e63e663ca", + "max": 3201, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_c1cb1e279bdd4de0a725dd51a8489563", + "value": 3201 } }, - "6b988b31851c4db6890479404c7011cf": { + "d8c83b57302a458aa3ee71cac9632455": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_37f6208a83084b92a458e21c197cad3f", + "placeholder": "​", + "style": "IPY_MODEL_1e1213f764474d7bbd426a5327829eb9", + "value": " 3.20k/3.20k [00:00<00:00, 68.1kB/s]" + } + }, + "08a04116a15043e88c1c50b76bc3a77b": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7280,10 +5627,10 @@ "width": null } }, - "6bfda8329c3741f4a0f175d41603c707": { + "e1f400ffbb124a56a281832bcc54eaf9": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7332,32 +5679,25 @@ "width": null } }, - "6c036b53916642e3993b40b66532f305": { + "a3ef8ad842a346df9ffc0f31725c9606": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_f02b5874bc1a4b29a0a8f65a455ae425", - "IPY_MODEL_73bbb254a9f94a2f90776da888b551c2", - "IPY_MODEL_4b400af9107d4cb09725a19a8978d33a" - ], - "layout": "IPY_MODEL_decda57cc9a7489fb32d384c270f4994" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" } }, - "6d274c81d3ed486a90598cee551db717": { + "fa605877967d4109a4fd496e63e663ca": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7406,14 +5746,30 @@ "width": null } }, - "6d8d46c27f5e4d23a9170c06fb8e6947": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", + "c1cb1e279bdd4de0a725dd51a8489563": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "37f6208a83084b92a458e21c197cad3f": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", @@ -7458,10 +5814,113 @@ "width": null } }, - "6e721aa59b9c4104b5eb823feacc4f42": { + "1e1213f764474d7bbd426a5327829eb9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "5492a2c2d56844bdabc9aaaab9bdc35f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_669272db738947e2b8102102a57bc87a", + "IPY_MODEL_dad194753c8e439c9d62285c0c06546a", + "IPY_MODEL_ae2f4d6301694356b5878fab0de3ea83" + ], + "layout": "IPY_MODEL_156fa699696c4e26b2842e89954d202b" + } + }, + "669272db738947e2b8102102a57bc87a": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b0cda3f2c228491bb6ce981267141f52", + "placeholder": "​", + "style": "IPY_MODEL_3fb43042ede944c485c1eadf21ebfa96", + "value": "classifier.ckpt: 100%" + } + }, + "dad194753c8e439c9d62285c0c06546a": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7eecca112ead43c9ab55a5220122ce97", + "max": 15856877, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_5f90e9766c3b44f0bded6715e12682d5", + "value": 15856877 + } + }, + "ae2f4d6301694356b5878fab0de3ea83": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b01b07d8119c4485ab5844ce7351aad8", + "placeholder": "​", + "style": "IPY_MODEL_bb435b975d2844879538ba5b00c377b5", + "value": " 15.9M/15.9M [00:00<00:00, 54.1MB/s]" + } + }, + "156fa699696c4e26b2842e89954d202b": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7510,25 +5969,10 @@ "width": null } }, - "6f667950dd5d48c5bd693d52494bfee3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "703e99ef518b4f40b1936147ce8d542d": { + "b0cda3f2c228491bb6ce981267141f52": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7577,70 +6021,10 @@ "width": null } }, - "708e0de686af4966a72d66fb174c1cfa": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_c78ec4ad3bfb443982281085989394fe", - "placeholder": "​", - "style": "IPY_MODEL_032cf630889f4f599dad2a0f718dd63e", - "value": " 2.04k/2.04k [00:00<00:00, 79.2kB/s]" - } - }, - "71cc5fea590e4eaa813a4b18ffcf2a19": { + "3fb43042ede944c485c1eadf21ebfa96": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "73bbb254a9f94a2f90776da888b551c2": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_22f2f7b6cad948efa54f0c748d427777", - "max": 2062, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_ba3d74aab1d44f44a3b795f4e4a9177e", - "value": 2062 - } - }, - "7569d59db923484399859632e3bcac12": { - "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -7652,10 +6036,10 @@ "description_width": "" } }, - "7597054472514485afa120d6266c91a5": { + "7eecca112ead43c9ab55a5220122ce97": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7704,49 +6088,26 @@ "width": null } }, - "7827a86376c94da99efb90f5842864ed": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_fa605877967d4109a4fd496e63e663ca", - "max": 3201, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_c1cb1e279bdd4de0a725dd51a8489563", - "value": 3201 - } - }, - "786cb3e450de464fa04f9ed4fbe073e1": { + "5f90e9766c3b44f0bded6715e12682d5": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", + "bar_color": null, "description_width": "" } }, - "789066d9a9e04bc7b34da287dae1ad14": { + "b01b07d8119c4485ab5844ce7351aad8": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7795,31 +6156,113 @@ "width": null } }, - "793b16cd7280425faa37ba7bf19e16c0": { + "bb435b975d2844879538ba5b00c377b5": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "1c0c9d45f86f4945965a4784109020ff": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_8462433da1b847b09f137a5017b575c8", + "IPY_MODEL_6535f9ad0436497dbcec30c1df342ac9", + "IPY_MODEL_4d02d845fa034829900635be82eb64ad" + ], + "layout": "IPY_MODEL_6d274c81d3ed486a90598cee551db717" + } + }, + "8462433da1b847b09f137a5017b575c8": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_4ee7e82441c74fc9b726d996a49c6908", + "layout": "IPY_MODEL_b58864d3bfb7426995ef989334687286", "placeholder": "​", - "style": "IPY_MODEL_cc1c35d92b754ff29989ecc023bb9e25", - "value": " 1000/1000 [00:00<00:00, 2329.73 examples/s]" + "style": "IPY_MODEL_04512216d85b42c4ae02d3f1083acbe9", + "value": "label_encoder.txt: 100%" } }, - "7c992442c78045e0962299728b49bbb5": { + "6535f9ad0436497dbcec30c1df342ac9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_10aea82371aa4b23bb1e2f906778f92e", + "max": 128619, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_935177cdab4a419ebb327a9641c2a6ff", + "value": 128619 + } + }, + "4d02d845fa034829900635be82eb64ad": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a10a271823244bce91dbc042bf838746", + "placeholder": "​", + "style": "IPY_MODEL_265bbe545b99430f85aa5884b64ac014", + "value": " 129k/129k [00:00<00:00, 3.88MB/s]" + } + }, + "6d274c81d3ed486a90598cee551db717": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7868,10 +6311,10 @@ "width": null } }, - "7dc5299d9e264f4d9dda9ff552d5d5cc": { + "b58864d3bfb7426995ef989334687286": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7920,10 +6363,25 @@ "width": null } }, - "7e7bb5871ded4f57ad44fb9e17116be1": { + "04512216d85b42c4ae02d3f1083acbe9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "10aea82371aa4b23bb1e2f906778f92e": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -7972,10 +6430,26 @@ "width": null } }, - "7eecca112ead43c9ab55a5220122ce97": { + "935177cdab4a419ebb327a9641c2a6ff": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "a10a271823244bce91dbc042bf838746": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8024,10 +6498,10 @@ "width": null } }, - "813e7e5696b84a0091524b551d94b1a6": { + "265bbe545b99430f85aa5884b64ac014": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -8039,25 +6513,98 @@ "description_width": "" } }, - "821bc686077d4d4faf73a98e60ef2262": { + "a60987317acd40278489533a2d9dd021": { "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "HBoxModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_c9662066695c43e7901ba019a0dc9e8c", + "IPY_MODEL_4ca762251949444f921863535a18e5c5", + "IPY_MODEL_d7142a382f884564921bcfcf65909287" + ], + "layout": "IPY_MODEL_13226fa6805041fdb7e3976e4577a66e" } }, - "82287f32ca37416b824ac2dcef8adcc1": { + "c9662066695c43e7901ba019a0dc9e8c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7c992442c78045e0962299728b49bbb5", + "placeholder": "​", + "style": "IPY_MODEL_a5fe768b739d4df896d15370e981b656", + "value": "config.json: 100%" + } + }, + "4ca762251949444f921863535a18e5c5": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4a7bd718c8874fc2bbd7a566e1da124d", + "max": 636, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_ea8fbaa445bd442b82bb60a67b0efcea", + "value": 636 + } + }, + "d7142a382f884564921bcfcf65909287": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_db1394f796f84b5295e16f1f8b2a526a", + "placeholder": "​", + "style": "IPY_MODEL_f44278459f804c7e9412f72c8cb4eef0", + "value": " 636/636 [00:00<00:00, 11.0kB/s]" + } + }, + "13226fa6805041fdb7e3976e4577a66e": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8106,10 +6653,10 @@ "width": null } }, - "82d5d05b953042f4bc7ad53a122d6a03": { + "7c992442c78045e0962299728b49bbb5": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8158,21 +6705,36 @@ "width": null } }, - "8306a7f425464783b14fd397b5a4be33": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", + "a5fe768b739d4df896d15370e981b656": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, + "_view_name": "StyleView", + "description_width": "" + } + }, + "4a7bd718c8874fc2bbd7a566e1da124d": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, "border": null, "bottom": null, "display": null, @@ -8210,31 +6772,26 @@ "width": null } }, - "8462433da1b847b09f137a5017b575c8": { + "ea8fbaa445bd442b82bb60a67b0efcea": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "ProgressStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_b58864d3bfb7426995ef989334687286", - "placeholder": "​", - "style": "IPY_MODEL_04512216d85b42c4ae02d3f1083acbe9", - "value": "label_encoder.txt: 100%" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" } }, - "869df80d498642f4b3a1d1825372cef7": { + "db1394f796f84b5295e16f1f8b2a526a": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8283,25 +6840,10 @@ "width": null } }, - "876341d2a2484e60a72caad3dc02c1b4": { + "f44278459f804c7e9412f72c8cb4eef0": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "877842a378c54836880b45d7b072c51b": { - "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -8313,78 +6855,98 @@ "description_width": "" } }, - "8b5abf1e77284e549e1ed7cdd100e2af": { + "33e739de4df54f96a276027d2d1f66ea": { "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "HBoxModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_2d3eb78c7b994f3cb2d57d80458c35d6", + "IPY_MODEL_de8ee1e97a0f4bbfa17281a0c067b5b1", + "IPY_MODEL_5ab5b7305633479494e991c26c2268a9" + ], + "layout": "IPY_MODEL_ab27bce16ed24effbddb7596ffe2c3c1" } }, - "8c299f76bb244a748838b967e5d93c2f": { + "2d3eb78c7b994f3cb2d57d80458c35d6": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "HTMLModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_5d30def7a2bb463baa858eb0eee9d094", + "placeholder": "​", + "style": "IPY_MODEL_06508d700e9c426b85f374381d3439d9", + "value": "pytorch_model.bin: 100%" } }, - "8c4bc267343547898e5daf05dfc1b244": { + "de8ee1e97a0f4bbfa17281a0c067b5b1": { "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_f511ee45542b4bc3be2009a8ff76b319", - "IPY_MODEL_b0a23f6a0e0641269686214f25829ffd", - "IPY_MODEL_3d4aed875264486187bc9ccb18881eb8" - ], - "layout": "IPY_MODEL_6e721aa59b9c4104b5eb823feacc4f42" + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_af4aeb90cfbc4937860ffd47ef7987e5", + "max": 50672453, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_8b5abf1e77284e549e1ed7cdd100e2af", + "value": 50672453 } }, - "8c8333ae0d3d4ba7813d4d91245823db": { + "5ab5b7305633479494e991c26c2268a9": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "HTMLModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_e550d62c5fb54e8c9be548e252a4ddc3", + "placeholder": "​", + "style": "IPY_MODEL_b51084470848412d9360ed3487aaf3f6", + "value": " 50.7M/50.7M [00:00<00:00, 103MB/s]" } }, - "8d117be740ff40b8b5bb62db6f0e8c79": { + "ab27bce16ed24effbddb7596ffe2c3c1": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8433,10 +6995,10 @@ "width": null } }, - "8e0bf7d4611641c091e87fbacbf10a19": { + "5d30def7a2bb463baa858eb0eee9d094": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8446,13 +7008,13 @@ "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, - "align_items": "center", + "align_items": null, "align_self": null, "border": null, "bottom": null, - "display": "flex", + "display": null, "flex": null, - "flex_flow": "column", + "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, @@ -8482,37 +7044,28 @@ "right": null, "top": null, "visibility": null, - "width": "50%" + "width": null } }, - "8f604dc7fccf4572821cb040ab5d8c5c": { + "06508d700e9c426b85f374381d3439d9": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_6b988b31851c4db6890479404c7011cf", - "max": 16887676, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_27b0e9d94b0a4d8cac920df223606d10", - "value": 16887676 + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" } }, - "91b3dc6e9a85404c96fd59cfb800d43f": { + "af4aeb90cfbc4937860ffd47ef7987e5": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8561,10 +7114,10 @@ "width": null } }, - "935177cdab4a419ebb327a9641c2a6ff": { + "8b5abf1e77284e549e1ed7cdd100e2af": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -8577,10 +7130,10 @@ "description_width": "" } }, - "95446dc9a4cc46469d1efa27c7896bfc": { + "e550d62c5fb54e8c9be548e252a4ddc3": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8629,34 +7182,47 @@ "width": null } }, - "958d0637ccad4af49815a2d137fee333": { + "b51084470848412d9360ed3487aaf3f6": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "2ebee62340c24076b6edeb96d233b5e0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_7597054472514485afa120d6266c91a5", - "max": 2108, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_6035b946f770456fbfd123adbb5e3be9", - "value": 2108 + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_dc0e721504184b778486802d47239e00", + "IPY_MODEL_4744d62b21e645b8bad84578aed387d3", + "IPY_MODEL_ef635c73df96463ea145fad659b04028" + ], + "layout": "IPY_MODEL_00adec96a5654f3a9d08c8331366f704" } }, - "969bec5ee95248d4a948965c74ff3311": { + "dc0e721504184b778486802d47239e00": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -8668,89 +7234,16 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_3e0e63681dfe4201ae9d8b7a370fca52", + "layout": "IPY_MODEL_3fd3b45e98ff4292a1444f89fc6ae95e", "placeholder": "​", - "style": "IPY_MODEL_630aa4eac24e481a9fdb9d999f0c8822", - "value": "embedding_model.ckpt: 100%" + "style": "IPY_MODEL_876341d2a2484e60a72caad3dc02c1b4", + "value": "Map: 100%" } }, - "974b89e5205a4487acb8577df5ea85e6": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "976a925fc43c42f1a580fd808d32023d": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_db176eb9bc144f5cbcacb0086d176571", - "placeholder": "​", - "style": "IPY_MODEL_fc0efaa60a504ffebb5e00bdc8c205b1", - "value": "spm_char.model: 100%" - } - }, - "980d09ee15b540a0868ed5e1cae7d867": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", + "4744d62b21e645b8bad84578aed387d3": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -8763,40 +7256,39 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_304787fbe0984b9f887fc948a8b888fc", - "max": 585476837, + "layout": "IPY_MODEL_4699dc096aa644b6add210252efa7334", + "max": 4112, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_e4138b99226846e9b4cfc4ea075329cd", - "value": 585476837 + "style": "IPY_MODEL_f2f329976e13413c9bcef0e56280d563", + "value": 4112 } }, - "992902679da84067b429893c7870b816": { + "ef635c73df96463ea145fad659b04028": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_af9cb18856474687a449ac515ede62e8", - "IPY_MODEL_db44aadde79b40f1850078024e910183", - "IPY_MODEL_f16031daae714a0181ddd0b31471f060" - ], - "layout": "IPY_MODEL_e7bdbfe7797a4b5db827f5b810d2d79b" + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_bd10c6180edc414f877b5ac363801a42", + "placeholder": "​", + "style": "IPY_MODEL_b818deafc75f4bfa8139ae6192dab50d", + "value": " 4112/4112 [01:21<00:00, 63.83 examples/s]" } }, - "99d7ad89bdd346909213390a050f412f": { + "00adec96a5654f3a9d08c8331366f704": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8845,47 +7337,10 @@ "width": null } }, - "9a84e7b2ed2e4854b3a27c4a7a6d7b29": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "CheckboxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "CheckboxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "CheckboxView", - "description": "Add token as git credential?", - "description_tooltip": null, - "disabled": false, - "indent": true, - "layout": "IPY_MODEL_7dc5299d9e264f4d9dda9ff552d5d5cc", - "style": "IPY_MODEL_034918f3b833496397f34caa9a0bfbb4", - "value": true - } - }, - "9aa2c30314774289a458d92cabf2e9e1": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "9b62f1cf2fe54ccda160abe4a281ca82": { + "3fd3b45e98ff4292a1444f89fc6ae95e": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -8934,34 +7389,25 @@ "width": null } }, - "9bf02a53411646439af4b7412d707923": { + "876341d2a2484e60a72caad3dc02c1b4": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_869df80d498642f4b3a1d1825372cef7", - "max": 238473, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_3518110403534f7f82a617d1bedc6315", - "value": 238473 + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" } }, - "9d8b343299174f5789bfef21e23cfff6": { + "4699dc096aa644b6add210252efa7334": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -9010,76 +7456,26 @@ "width": null } }, - "9d901610487e4d7389072038d0e5d72d": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_efeef3aa079d4bf4bc4c5049f9c74e16", - "placeholder": "​", - "style": "IPY_MODEL_821bc686077d4d4faf73a98e60ef2262", - "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks.
" - } - }, - "9defb63d40414377962be7a45fe04863": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "VBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "VBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "VBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_346edbb27fec4479ad74331561fe6d4f", - "IPY_MODEL_382582721b924a77a6ed9ebf2d0e78c6", - "IPY_MODEL_f1e85d48269a4675aa3eb1484d5ebbf7", - "IPY_MODEL_bd810380dabe446d874fbcdbf0a2a815" - ], - "layout": "IPY_MODEL_8e0bf7d4611641c091e87fbacbf10a19" - } - }, - "9e64b696d550460792e4829c6ebd5342": { + "f2f329976e13413c9bcef0e56280d563": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "ProgressStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_6a540a4e656b4286aa5135fc4ea66ece", - "IPY_MODEL_08cbe5b1b931421c8feb029485a4b122", - "IPY_MODEL_28052ac1a482483fb430936be0848b38" - ], - "layout": "IPY_MODEL_703e99ef518b4f40b1936147ce8d542d" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" } }, - "9ecef1d0b473411b914eed7fa043478e": { + "bd10c6180edc414f877b5ac363801a42": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -9128,10 +7524,10 @@ "width": null } }, - "a06f4c8a4ca544339eebffd9cbacb32e": { + "b818deafc75f4bfa8139ae6192dab50d": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -9143,116 +7539,32 @@ "description_width": "" } }, - "a10a271823244bce91dbc042bf838746": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "a15ad78eb7e249a2ae8f1a4e0b0e359e": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", + "2993094c7ff6425eab9bb0b1bdf1d7ac": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_3bd4aa82001248acb3758f0ff98fe64c", - "max": 4112, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_494b73ce426e44da9601305d859f484c", - "value": 4112 - } - }, - "a33b6fea82cb4c31a00bc7da57837fa3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "a3ef8ad842a346df9ffc0f31725c9606": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_fd6cb6748b1a4d83bbd3c1f9bc9293c9", + "IPY_MODEL_a15ad78eb7e249a2ae8f1a4e0b0e359e", + "IPY_MODEL_39f6a7a3035a4c53bebc34e7a90ad14c" + ], + "layout": "IPY_MODEL_078823ec9ed64a58abc1ee0a7d55976a" } }, - "a3f2bf1d001c4f2d8571d2a4db8972d1": { + "fd6cb6748b1a4d83bbd3c1f9bc9293c9": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -9264,75 +7576,61 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_95446dc9a4cc46469d1efa27c7896bfc", + "layout": "IPY_MODEL_b710b2c93fcb437eb220dbd57ba1a235", "placeholder": "​", - "style": "IPY_MODEL_3cd2ea08c82e49a08396e31dfead7f6f", - "value": " 190/190 [00:00<00:00, 12.6kB/s]" - } - }, - "a5fe768b739d4df896d15370e981b656": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "style": "IPY_MODEL_4acb801fd07e4e1db048921d83fad83f", + "value": "Filter: 100%" } }, - "a60987317acd40278489533a2d9dd021": { + "a15ad78eb7e249a2ae8f1a4e0b0e359e": { "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_c9662066695c43e7901ba019a0dc9e8c", - "IPY_MODEL_4ca762251949444f921863535a18e5c5", - "IPY_MODEL_d7142a382f884564921bcfcf65909287" - ], - "layout": "IPY_MODEL_13226fa6805041fdb7e3976e4577a66e" + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_3bd4aa82001248acb3758f0ff98fe64c", + "max": 4112, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_494b73ce426e44da9601305d859f484c", + "value": 4112 } }, - "a617fca4345c4d21a6c44d5ef8246f91": { + "39f6a7a3035a4c53bebc34e7a90ad14c": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_3109d5c2ffe04d5ebf296cc26a334a38", - "IPY_MODEL_4d97d63c12ab4c37b53207cf91ac9794", - "IPY_MODEL_a3f2bf1d001c4f2d8571d2a4db8972d1" - ], - "layout": "IPY_MODEL_e27fcac6c1be4ecc89028aa8368e6e89" + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_c350945401cb48968758c0674598a855", + "placeholder": "​", + "style": "IPY_MODEL_0194367f515647b1ae5bc638d212c2ce", + "value": " 4112/4112 [00:00<00:00, 38198.02 examples/s]" } }, - "a903a041f8f34e95b7eb95e7680e68af": { + "078823ec9ed64a58abc1ee0a7d55976a": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -9381,10 +7679,10 @@ "width": null } }, - "a99df968c26040e3a9d8465d539b7844": { + "b710b2c93fcb437eb220dbd57ba1a235": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -9433,49 +7731,10 @@ "width": null } }, - "aa43ed4fb93c4089b5a9e64cb6adb9f3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_b821ee6883804da09ca3c35c510dd8da", - "max": 255659282, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_596d960afbb24861a220d63745b271a6", - "value": 255659282 - } - }, - "aa7bf7b3cc7441888151beffb6d30321": { + "4acb801fd07e4e1db048921d83fad83f": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "aaebe1f70f4f4d639d3ecbba9f406f8b": { - "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -9487,10 +7746,10 @@ "description_width": "" } }, - "ab27bce16ed24effbddb7596ffe2c3c1": { + "3bd4aa82001248acb3758f0ff98fe64c": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -9539,31 +7798,26 @@ "width": null } }, - "ae2f4d6301694356b5878fab0de3ea83": { + "494b73ce426e44da9601305d859f484c": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "ProgressStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_b01b07d8119c4485ab5844ce7351aad8", - "placeholder": "​", - "style": "IPY_MODEL_bb435b975d2844879538ba5b00c377b5", - "value": " 15.9M/15.9M [00:00<00:00, 54.1MB/s]" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" } }, - "af01cdbb16dd490984a749d2da6eff34": { + "c350945401cb48968758c0674598a855": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -9612,10 +7866,10 @@ "width": null } }, - "af1e15c4f52e4ea5886d1631de2fbe39": { + "0194367f515647b1ae5bc638d212c2ce": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -9627,84 +7881,121 @@ "description_width": "" } }, - "af4aeb90cfbc4937860ffd47ef7987e5": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", + "9defb63d40414377962be7a45fe04863": { + "model_module": "@jupyter-widgets/controls", + "model_name": "VBoxModel", + "model_module_version": "1.5.0", "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "VBoxModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "VBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_346edbb27fec4479ad74331561fe6d4f", + "IPY_MODEL_382582721b924a77a6ed9ebf2d0e78c6", + "IPY_MODEL_f1e85d48269a4675aa3eb1484d5ebbf7", + "IPY_MODEL_bd810380dabe446d874fbcdbf0a2a815" + ], + "layout": "IPY_MODEL_8e0bf7d4611641c091e87fbacbf10a19" } }, - "af584652d0304a899e66314d61726323": { + "4bdb55d30a0b4b648c082f2cf5921383": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_3b74fdd0043949548e50b1d87413505b", - "IPY_MODEL_958d0637ccad4af49815a2d137fee333", - "IPY_MODEL_e10a5c2d674c4948978e0bc3fc2e8b0d" - ], - "layout": "IPY_MODEL_68a15f79b7ab42eaa0b14086f2b54ed6" + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_c4660f3058d14daba1940d89e200b65d", + "placeholder": "​", + "style": "IPY_MODEL_31ed87b6e80b4822b430c51ae043edcf", + "value": "

Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
" } }, - "af9cb18856474687a449ac515ede62e8": { + "b9d136e1b7944a08a3b206be697e8bcd": { + "model_module": "@jupyter-widgets/controls", + "model_name": "PasswordModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "PasswordModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "PasswordView", + "continuous_update": true, + "description": "Token:", + "description_tooltip": null, + "disabled": false, + "layout": "IPY_MODEL_4edcc714fca4485190e973ed83325af1", + "placeholder": "​", + "style": "IPY_MODEL_8c8333ae0d3d4ba7813d4d91245823db", + "value": "" + } + }, + "9a84e7b2ed2e4854b3a27c4a7a6d7b29": { + "model_module": "@jupyter-widgets/controls", + "model_name": "CheckboxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "CheckboxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "CheckboxView", + "description": "Add token as git credential?", + "description_tooltip": null, + "disabled": false, + "indent": true, + "layout": "IPY_MODEL_7dc5299d9e264f4d9dda9ff552d5d5cc", + "style": "IPY_MODEL_034918f3b833496397f34caa9a0bfbb4", + "value": true + } + }, + "17f05d9f756e466eba646e8dca6a89e3": { "model_module": "@jupyter-widgets/controls", + "model_name": "ButtonModel", "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ButtonView", + "button_style": "", + "description": "Login", + "disabled": false, + "icon": "", + "layout": "IPY_MODEL_0a595220c4004b6ca316c47babe4e5a7", + "style": "IPY_MODEL_1e34bc54a39b42b1a5a2ece20823ca3f", + "tooltip": "" + } + }, + "9d901610487e4d7389072038d0e5d72d": { + "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -9716,16 +8007,16 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_a99df968c26040e3a9d8465d539b7844", + "layout": "IPY_MODEL_efeef3aa079d4bf4bc4c5049f9c74e16", "placeholder": "​", - "style": "IPY_MODEL_45e7d7b493fb45d1b71b0f42464a9ac8", - "value": "special_tokens_map.json: 100%" + "style": "IPY_MODEL_821bc686077d4d4faf73a98e60ef2262", + "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. " } }, - "afecd676c8024a89bc20165215fc7f5c": { + "8e0bf7d4611641c091e87fbacbf10a19": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -9735,13 +8026,13 @@ "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, - "align_items": null, + "align_items": "center", "align_self": null, "border": null, "bottom": null, - "display": null, + "display": "flex", "flex": null, - "flex_flow": null, + "flex_flow": "column", "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, @@ -9771,13 +8062,13 @@ "right": null, "top": null, "visibility": null, - "width": null + "width": "50%" } }, - "b01b07d8119c4485ab5844ce7351aad8": { + "c4660f3058d14daba1940d89e200b65d": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -9826,10 +8117,10 @@ "width": null } }, - "b029a4f4c27340808012eab6ba5573ed": { + "31ed87b6e80b4822b430c51ae043edcf": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -9841,34 +8132,10 @@ "description_width": "" } }, - "b0a23f6a0e0641269686214f25829ffd": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_3d0c025d4bab42f1b53a808aeb9ba942", - "max": 4112, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_3b0b3cb12bd34d2c8898a1bc0a938c4c", - "value": 4112 - } - }, - "b0cda3f2c228491bb6ce981267141f52": { + "4edcc714fca4485190e973ed83325af1": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -9917,41 +8184,10 @@ "width": null } }, - "b257195cf3314cb4bc3aeddc4da142b9": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "b2612a5852164e98bc46b7242bf4ff4d": { + "8c8333ae0d3d4ba7813d4d91245823db": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "b51084470848412d9360ed3487aaf3f6": { - "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -9963,10 +8199,10 @@ "description_width": "" } }, - "b58864d3bfb7426995ef989334687286": { + "7dc5299d9e264f4d9dda9ff552d5d5cc": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10015,14 +8251,29 @@ "width": null } }, - "b5cc29850b5a4fcfb3cd368d35081736": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", + "034918f3b833496397f34caa9a0bfbb4": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "0a595220c4004b6ca316c47babe4e5a7": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", @@ -10067,10 +8318,26 @@ "width": null } }, - "b710b2c93fcb437eb220dbd57ba1a235": { + "1e34bc54a39b42b1a5a2ece20823ca3f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ButtonStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "button_color": null, + "font_weight": "" + } + }, + "efeef3aa079d4bf4bc4c5049f9c74e16": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10119,10 +8386,10 @@ "width": null } }, - "b818deafc75f4bfa8139ae6192dab50d": { + "821bc686077d4d4faf73a98e60ef2262": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -10134,10 +8401,31 @@ "description_width": "" } }, - "b821ee6883804da09ca3c35c510dd8da": { + "e6a2cb79b3a14ceb96e44b93529a1b17": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_18f235d673c1422abc9a7a897295aaf4", + "placeholder": "​", + "style": "IPY_MODEL_e87df5c1d1fb4d19bd7e8663f39a9073", + "value": "Connecting..." + } + }, + "18f235d673c1422abc9a7a897295aaf4": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10186,32 +8474,10 @@ "width": null } }, - "b89a27c225cf4e49860c8f62e32efaf6": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_fa94d043df65408a8418026350b837a1", - "IPY_MODEL_169d1b4d3773401688dc1884d6532788", - "IPY_MODEL_beb62f2bd7a24f9a82159ed016abb9b5" - ], - "layout": "IPY_MODEL_601c4fb9215444efb45f55852abd41d5" - } - }, - "b9290e687dcd420abfc46b43639fed28": { + "e87df5c1d1fb4d19bd7e8663f39a9073": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -10223,100 +8489,94 @@ "description_width": "" } }, - "b9d136e1b7944a08a3b206be697e8bcd": { + "346edbb27fec4479ad74331561fe6d4f": { "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", "model_module_version": "1.5.0", - "model_name": "PasswordModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "PasswordModel", + "_model_name": "LabelModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "PasswordView", - "continuous_update": true, - "description": "Token:", + "_view_name": "LabelView", + "description": "", "description_tooltip": null, - "disabled": false, - "layout": "IPY_MODEL_4edcc714fca4485190e973ed83325af1", + "layout": "IPY_MODEL_5942dd51d8014d32a6400698fa84f88e", "placeholder": "​", - "style": "IPY_MODEL_8c8333ae0d3d4ba7813d4d91245823db", - "value": "" - } - }, - "ba3d74aab1d44f44a3b795f4e4a9177e": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" + "style": "IPY_MODEL_813e7e5696b84a0091524b551d94b1a6", + "value": "Token is valid (permission: write)." } }, - "bb212e00ea9b416db52167e0a64608ee": { + "382582721b924a77a6ed9ebf2d0e78c6": { "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "LabelModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_59f995c679f843eba17be9f2cab2b5ca", + "placeholder": "​", + "style": "IPY_MODEL_aa7bf7b3cc7441888151beffb6d30321", + "value": "Your token has been saved in your configured git credential helpers (store)." } }, - "bb435b975d2844879538ba5b00c377b5": { + "f1e85d48269a4675aa3eb1484d5ebbf7": { "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "LabelModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a903a041f8f34e95b7eb95e7680e68af", + "placeholder": "​", + "style": "IPY_MODEL_499ae3562b0e4636a5526230245d502a", + "value": "Your token has been saved to /root/.cache/huggingface/token" } }, - "bcd4e9d178c944f6973b2d62fa1e5538": { + "bd810380dabe446d874fbcdbf0a2a815": { "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", "model_module_version": "1.5.0", - "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "LabelModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HTMLView", + "_view_name": "LabelView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_d432e91ec63b4655a50bc775ee74aab4", + "layout": "IPY_MODEL_c5b791315d534952b9087a66d94a49a4", "placeholder": "​", - "style": "IPY_MODEL_af1e15c4f52e4ea5886d1631de2fbe39", - "value": " 578M/578M [00:23<00:00, 24.6MB/s]" + "style": "IPY_MODEL_d3d5fd89f4df4f278529a4d959f64d5f", + "value": "Login successful" } }, - "bd10c6180edc414f877b5ac363801a42": { + "5942dd51d8014d32a6400698fa84f88e": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10365,117 +8625,29 @@ "width": null } }, - "bd810380dabe446d874fbcdbf0a2a815": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "LabelModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "LabelModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "LabelView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_c5b791315d534952b9087a66d94a49a4", - "placeholder": "​", - "style": "IPY_MODEL_d3d5fd89f4df4f278529a4d959f64d5f", - "value": "Login successful" - } - }, - "bd858f248a124f14833b044f7b0b71e5": { + "813e7e5696b84a0091524b551d94b1a6": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", - "bar_color": null, "description_width": "" } }, - "be44a4398328449daebb6bd48e2519f7": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_d0f6e0eefec74d9aa2a0a00868c77a55", - "max": 577789320, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_bd858f248a124f14833b044f7b0b71e5", - "value": 577789320 - } - }, - "beb62f2bd7a24f9a82159ed016abb9b5": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", + "59f995c679f843eba17be9f2cab2b5ca": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_91b3dc6e9a85404c96fd59cfb800d43f", - "placeholder": "​", - "style": "IPY_MODEL_b9290e687dcd420abfc46b43639fed28", - "value": " 232/232 [00:00<00:00, 15.5kB/s]" - } - }, - "c1052b9d43984c67b28c50c2a9d620a3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_7e7bb5871ded4f57ad44fb9e17116be1", - "placeholder": "​", - "style": "IPY_MODEL_b029a4f4c27340808012eab6ba5573ed", - "value": "Generating test split: 100%" - } - }, - "c16b239971bc41d8be09280b34536fd4": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", @@ -10520,10 +8692,25 @@ "width": null } }, - "c1b4ea7cfc0d434dbb68027af48a5f07": { + "aa7bf7b3cc7441888151beffb6d30321": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "a903a041f8f34e95b7eb95e7680e68af": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10572,26 +8759,25 @@ "width": null } }, - "c1cb1e279bdd4de0a725dd51a8489563": { + "499ae3562b0e4636a5526230245d502a": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", - "bar_color": null, "description_width": "" } }, - "c350945401cb48968758c0674598a855": { + "c5b791315d534952b9087a66d94a49a4": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10640,10 +8826,113 @@ "width": null } }, - "c3e26506549144279b7b60c3382b4486": { + "d3d5fd89f4df4f278529a4d959f64d5f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "456aa13fa38c4c01b9f43570e31556fe": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_ec7ac27d32c44b40ac8fd18a7700962d", + "IPY_MODEL_fbeb5a0f2394434fb67644f452dcb6b2", + "IPY_MODEL_f22ab8b84c9a406d9383a1253576cf62" + ], + "layout": "IPY_MODEL_3915aa47172546afb3f09ea1f7c5b947" + } + }, + "ec7ac27d32c44b40ac8fd18a7700962d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_308b5dd72e6f4ea39d9be4c2e4a02512", + "placeholder": "​", + "style": "IPY_MODEL_9aa2c30314774289a458d92cabf2e9e1", + "value": "events.out.tfevents.1721676197.d34fde1d2e44.268.2: 100%" + } + }, + "fbeb5a0f2394434fb67644f452dcb6b2": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4d5bdff9982e40138888bc9c72f9233e", + "max": 101197, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_2c9002098b114841b511b97c5fa39f14", + "value": 101197 + } + }, + "f22ab8b84c9a406d9383a1253576cf62": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_fe75e4e2a67749b49efe29817c9148db", + "placeholder": "​", + "style": "IPY_MODEL_1660e3387e094116b87f3a8f04782124", + "value": " 101k/101k [00:00<00:00, 135kB/s]" + } + }, + "3915aa47172546afb3f09ea1f7c5b947": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10692,10 +8981,10 @@ "width": null } }, - "c4660f3058d14daba1940d89e200b65d": { + "308b5dd72e6f4ea39d9be4c2e4a02512": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10744,10 +9033,25 @@ "width": null } }, - "c5b791315d534952b9087a66d94a49a4": { + "9aa2c30314774289a458d92cabf2e9e1": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "4d5bdff9982e40138888bc9c72f9233e": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10796,10 +9100,26 @@ "width": null } }, - "c78ec4ad3bfb443982281085989394fe": { + "2c9002098b114841b511b97c5fa39f14": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "fe75e4e2a67749b49efe29817c9148db": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -10848,114 +9168,47 @@ "width": null } }, - "c8be0944b2d14e47a2f7909138527aaf": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", + "1660e3387e094116b87f3a8f04782124": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null + "_view_name": "StyleView", + "description_width": "" } }, - "c8e59f437cc74c4da6fbdab1f69630dd": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", + "af584652d0304a899e66314d61726323": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_3b74fdd0043949548e50b1d87413505b", + "IPY_MODEL_958d0637ccad4af49815a2d137fee333", + "IPY_MODEL_e10a5c2d674c4948978e0bc3fc2e8b0d" + ], + "layout": "IPY_MODEL_68a15f79b7ab42eaa0b14086f2b54ed6" } }, - "c9662066695c43e7901ba019a0dc9e8c": { + "3b74fdd0043949548e50b1d87413505b": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -10967,47 +9220,61 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_7c992442c78045e0962299728b49bbb5", + "layout": "IPY_MODEL_6916935a59f94d6e95449be55732c80c", "placeholder": "​", - "style": "IPY_MODEL_a5fe768b739d4df896d15370e981b656", + "style": "IPY_MODEL_cef8c2e1224b4f0eb21e4963d53431b5", "value": "config.json: 100%" } }, - "caaca6fb45eb453dbd2d8bb4ff5d3d52": { + "958d0637ccad4af49815a2d137fee333": { "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "FloatProgressModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7597054472514485afa120d6266c91a5", + "max": 2108, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6035b946f770456fbfd123adbb5e3be9", + "value": 2108 } }, - "cc1c35d92b754ff29989ecc023bb9e25": { + "e10a5c2d674c4948978e0bc3fc2e8b0d": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "HTMLModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_64eb31cf8d59468ea56a8e58c71d8122", + "placeholder": "​", + "style": "IPY_MODEL_0900daeba5cf4cb29d00a9c5ed5ad330", + "value": " 2.11k/2.11k [00:00<00:00, 31.4kB/s]" } }, - "cdb0d85e5dcb4d5998049b784acb00be": { + "68a15f79b7ab42eaa0b14086f2b54ed6": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11056,10 +9323,10 @@ "width": null } }, - "ced524c3f07b40e792db0bf1e9c3fe92": { + "6916935a59f94d6e95449be55732c80c": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11110,8 +9377,8 @@ }, "cef8c2e1224b4f0eb21e4963d53431b5": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -11123,62 +9390,10 @@ "description_width": "" } }, - "d00a6c69c91747ee952a78cabb4b5f73": { + "7597054472514485afa120d6266c91a5": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "d0f6e0eefec74d9aa2a0a00868c77a55": { - "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", - "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11227,25 +9442,26 @@ "width": null } }, - "d3d5fd89f4df4f278529a4d959f64d5f": { + "6035b946f770456fbfd123adbb5e3be9": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", + "bar_color": null, "description_width": "" } }, - "d432e91ec63b4655a50bc775ee74aab4": { + "64eb31cf8d59468ea56a8e58c71d8122": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11294,34 +9510,47 @@ "width": null } }, - "d6f7f58dd281478483d66e9d42dd8d9e": { + "0900daeba5cf4cb29d00a9c5ed5ad330": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "054b003700514935960c7ee0895b8c8e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_4cbded0a06734d1b9df19c952e13f08a", - "max": 113869079, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_4664dcf8fe2945978d5033f996ae5e10", - "value": 113869079 + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_2dcbcbfcbb3c455a8beee0d7f4c12c05", + "IPY_MODEL_be44a4398328449daebb6bd48e2519f7", + "IPY_MODEL_bcd4e9d178c944f6973b2d62fa1e5538" + ], + "layout": "IPY_MODEL_d8419ef35db5403c862e8321572ad376" } }, - "d7142a382f884564921bcfcf65909287": { + "2dcbcbfcbb3c455a8beee0d7f4c12c05": { "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", "model_name": "HTMLModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -11333,16 +9562,61 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_db1394f796f84b5295e16f1f8b2a526a", + "layout": "IPY_MODEL_af01cdbb16dd490984a749d2da6eff34", "placeholder": "​", - "style": "IPY_MODEL_f44278459f804c7e9412f72c8cb4eef0", - "value": " 636/636 [00:00<00:00, 11.0kB/s]" + "style": "IPY_MODEL_54783e715ad0408eaa512f7d28a374b2", + "value": "model.safetensors: 100%" } }, - "d7cd149116154f98aad430d857c46381": { + "be44a4398328449daebb6bd48e2519f7": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_d0f6e0eefec74d9aa2a0a00868c77a55", + "max": 577789320, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_bd858f248a124f14833b044f7b0b71e5", + "value": 577789320 + } + }, + "bcd4e9d178c944f6973b2d62fa1e5538": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_d432e91ec63b4655a50bc775ee74aab4", + "placeholder": "​", + "style": "IPY_MODEL_af1e15c4f52e4ea5886d1631de2fbe39", + "value": " 578M/578M [00:23<00:00, 24.6MB/s]" + } + }, + "d8419ef35db5403c862e8321572ad376": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11391,25 +9665,10 @@ "width": null } }, - "d827d96e5328476c80a212fad5570c78": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "d8419ef35db5403c862e8321572ad376": { + "af01cdbb16dd490984a749d2da6eff34": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11458,77 +9717,25 @@ "width": null } }, - "d8c83b57302a458aa3ee71cac9632455": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_37f6208a83084b92a458e21c197cad3f", - "placeholder": "​", - "style": "IPY_MODEL_1e1213f764474d7bbd426a5327829eb9", - "value": " 3.20k/3.20k [00:00<00:00, 68.1kB/s]" - } - }, - "d8e8d1b0adcd4d47b061aad1486604cb": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_1f15ee66a1f24e41b5630d5616243a7b", - "IPY_MODEL_651b513c24e24a5990591f95f24a4c0a", - "IPY_MODEL_708e0de686af4966a72d66fb174c1cfa" - ], - "layout": "IPY_MODEL_f46eb3dacc954c729a2c2b44d91a5382" - } - }, - "dad194753c8e439c9d62285c0c06546a": { + "54783e715ad0408eaa512f7d28a374b2": { "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_7eecca112ead43c9ab55a5220122ce97", - "max": 15856877, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_5f90e9766c3b44f0bded6715e12682d5", - "value": 15856877 + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" } }, - "db1394f796f84b5295e16f1f8b2a526a": { + "d0f6e0eefec74d9aa2a0a00868c77a55": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11577,10 +9784,26 @@ "width": null } }, - "db176eb9bc144f5cbcacb0086d176571": { + "bd858f248a124f14833b044f7b0b71e5": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "d432e91ec63b4655a50bc775ee74aab4": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11629,10 +9852,68 @@ "width": null } }, - "db2c1cf6f56c4aefa44e2da5b1b85a67": { + "af1e15c4f52e4ea5886d1631de2fbe39": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "a617fca4345c4d21a6c44d5ef8246f91": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_3109d5c2ffe04d5ebf296cc26a334a38", + "IPY_MODEL_4d97d63c12ab4c37b53207cf91ac9794", + "IPY_MODEL_a3f2bf1d001c4f2d8571d2a4db8972d1" + ], + "layout": "IPY_MODEL_e27fcac6c1be4ecc89028aa8368e6e89" + } + }, + "3109d5c2ffe04d5ebf296cc26a334a38": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_c1b4ea7cfc0d434dbb68027af48a5f07", + "placeholder": "​", + "style": "IPY_MODEL_5e1fd59b51d1459da614ab5d51116d59", + "value": "generation_config.json: 100%" + } + }, + "4d97d63c12ab4c37b53207cf91ac9794": { + "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -11645,42 +9926,39 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_82287f32ca37416b824ac2dcef8adcc1", - "max": 4112, + "layout": "IPY_MODEL_ced524c3f07b40e792db0bf1e9c3fe92", + "max": 190, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_e376e343655744e0b09f3fe3212c1d41", - "value": 4112 + "style": "IPY_MODEL_b257195cf3314cb4bc3aeddc4da142b9", + "value": 190 } }, - "db44aadde79b40f1850078024e910183": { + "a3f2bf1d001c4f2d8571d2a4db8972d1": { "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", + "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_1eabe7caf021425a83295181e16a573d", - "max": 234, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_e281d772babb4a2dbb1a949e6a5a440c", - "value": 234 + "layout": "IPY_MODEL_95446dc9a4cc46469d1efa27c7896bfc", + "placeholder": "​", + "style": "IPY_MODEL_3cd2ea08c82e49a08396e31dfead7f6f", + "value": " 190/190 [00:00<00:00, 12.6kB/s]" } }, - "db9886b3bdf24a7690e5464275656dca": { + "e27fcac6c1be4ecc89028aa8368e6e89": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11729,55 +10007,145 @@ "width": null } }, - "dc0e721504184b778486802d47239e00": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], + "c1b4ea7cfc0d434dbb68027af48a5f07": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "5e1fd59b51d1459da614ab5d51116d59": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_3fd3b45e98ff4292a1444f89fc6ae95e", - "placeholder": "​", - "style": "IPY_MODEL_876341d2a2484e60a72caad3dc02c1b4", - "value": "Map: 100%" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" } }, - "de8ee1e97a0f4bbfa17281a0c067b5b1": { + "ced524c3f07b40e792db0bf1e9c3fe92": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b257195cf3314cb4bc3aeddc4da142b9": { "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "ProgressStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_af4aeb90cfbc4937860ffd47ef7987e5", - "max": 50672453, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_8b5abf1e77284e549e1ed7cdd100e2af", - "value": 50672453 + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" } }, - "decda57cc9a7489fb32d384c270f4994": { + "95446dc9a4cc46469d1efa27c7896bfc": { "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", "model_name": "LayoutModel", + "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -11826,1327 +10194,3026 @@ "width": null } }, - "df0da2ae6ac6428aac6b61752c52bcc7": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_69ee5b1b8e864d8180913e5ab758b630", - "placeholder": "​", - "style": "IPY_MODEL_6f667950dd5d48c5bd693d52494bfee3", - "value": "Downloading data: 100%" - } + "3cd2ea08c82e49a08396e31dfead7f6f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + } + } + }, + "accelerator": "GPU" + }, + "cells": [ + { + "cell_type": "markdown", + "source": [ + "# Fine-tuning SpeechT5 for multilingual TTS" + ], + "metadata": { + "id": "2RosoNrCxVng" + } + }, + { + "cell_type": "markdown", + "source": [ + "This notebook demonstrates how to fine-tune the SpeechT5 model from 🤗 Transformers on the **text-to-speech** task.\n", + "\n", + "The unique thing about SpeechT5 is that the model is first pre-trained on a combination of speech-to-text and text-to-speech data, so that it learns a unified space of hidden representations shared by both text and speech. This allows us to fine-tune the same pretrained model on different tasks. Read more about SpeechT5 [in our blog post](https://huggingface.co/blog/speecht5).\n", + "\n", + "In this notebook we will start from an existing fine-tuned TTS model that was originally trained on English speech from LibriTTS, and fine-tune it for the Urdu Language.\n", + "\n", + "This TTS model will support multiple speakers through x-vector speaker embeddings." + ], + "metadata": { + "id": "uELTb9CcOaCp" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Install required packages\n", + "\n", + "We install Transformers from GitHub since not all the SpeechT5 features we need have been merged into an official release yet.\n" + ], + "metadata": { + "id": "5xB8fh-ht4kK" + } + }, + { + "cell_type": "code", + "source": [ + "!pip install datasets soundfile speechbrain" + ], + "metadata": { + "id": "xJe8TF3atyqL", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "964d222e-94c0-4de8-be56-59d67c3c148d" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Collecting datasets\n", + " Downloading datasets-2.20.0-py3-none-any.whl (547 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m547.8/547.8 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: soundfile in /usr/local/lib/python3.10/dist-packages (0.12.1)\n", + "Collecting speechbrain\n", + " Downloading speechbrain-1.0.0-py3-none-any.whl (760 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m760.1/760.1 kB\u001b[0m \u001b[31m38.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.15.4)\n", + "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.25.2)\n", + "Collecting pyarrow>=15.0.0 (from datasets)\n", + " Downloading pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl (39.9 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m39.9/39.9 MB\u001b[0m \u001b[31m13.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n", + "Collecting dill<0.3.9,>=0.3.0 (from datasets)\n", + " Downloading dill-0.3.8-py3-none-any.whl (116 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m15.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.0.3)\n", + "Collecting requests>=2.32.2 (from datasets)\n", + " Downloading requests-2.32.3-py3-none-any.whl (64 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m64.9/64.9 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: tqdm>=4.66.3 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.4)\n", + "Collecting xxhash (from datasets)\n", + " Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m16.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting multiprocess (from datasets)\n", + " Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: fsspec[http]<=2024.5.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n", + "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.5)\n", + "Requirement already satisfied: huggingface-hub>=0.21.2 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.23.5)\n", + "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.1)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n", + "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.10/dist-packages (from soundfile) (1.16.0)\n", + "Collecting hyperpyyaml (from speechbrain)\n", + " Downloading HyperPyYAML-1.2.2-py3-none-any.whl (16 kB)\n", + "Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from speechbrain) (1.4.2)\n", + "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from speechbrain) (1.11.4)\n", + "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from speechbrain) (0.1.99)\n", + "Requirement already satisfied: torch>=1.9 in /usr/local/lib/python3.10/dist-packages (from speechbrain) (2.3.1+cu121)\n", + "Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (from speechbrain) (2.3.1+cu121)\n", + "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0->soundfile) (2.22)\n", + "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n", + "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n", + "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n", + "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n", + "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n", + "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.21.2->datasets) (4.12.2)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (3.7)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (2024.7.4)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain) (1.13.0)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain) (3.3)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain) (3.1.4)\n", + "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n", + "Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n", + "Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n", + "Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n", + "Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n", + "Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n", + "Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n", + "Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n", + "Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n", + "Collecting nvidia-nccl-cu12==2.20.5 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl (176.2 MB)\n", + "Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.9->speechbrain)\n", + " Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n", + "Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain) (2.3.1)\n", + "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.9->speechbrain)\n", + " Downloading nvidia_nvjitlink_cu12-12.5.82-py3-none-manylinux2014_x86_64.whl (21.3 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.3/21.3 MB\u001b[0m \u001b[31m62.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting ruamel.yaml>=0.17.28 (from hyperpyyaml->speechbrain)\n", + " Downloading ruamel.yaml-0.18.6-py3-none-any.whl (117 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.8/117.8 kB\u001b[0m \u001b[31m15.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n", + "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n", + "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n", + "Collecting ruamel.yaml.clib>=0.2.7 (from ruamel.yaml>=0.17.28->hyperpyyaml->speechbrain)\n", + " Downloading ruamel.yaml.clib-0.2.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl (526 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m526.7/526.7 kB\u001b[0m \u001b[31m48.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.9->speechbrain) (2.1.5)\n", + "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.9->speechbrain) (1.3.0)\n", + "Installing collected packages: xxhash, ruamel.yaml.clib, requests, pyarrow, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, dill, ruamel.yaml, nvidia-cusparse-cu12, nvidia-cudnn-cu12, multiprocess, nvidia-cusolver-cu12, hyperpyyaml, datasets, speechbrain\n", + " Attempting uninstall: requests\n", + " Found existing installation: requests 2.31.0\n", + " Uninstalling requests-2.31.0:\n", + " Successfully uninstalled requests-2.31.0\n", + " Attempting uninstall: pyarrow\n", + " Found existing installation: pyarrow 14.0.2\n", + " Uninstalling pyarrow-14.0.2:\n", + " Successfully uninstalled pyarrow-14.0.2\n", + "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", + "cudf-cu12 24.4.1 requires pyarrow<15.0.0a0,>=14.0.1, but you have pyarrow 17.0.0 which is incompatible.\n", + "google-colab 1.0.0 requires requests==2.31.0, but you have requests 2.32.3 which is incompatible.\n", + "ibis-framework 8.0.0 requires pyarrow<16,>=2, but you have pyarrow 17.0.0 which is incompatible.\u001b[0m\u001b[31m\n", + "\u001b[0mSuccessfully installed datasets-2.20.0 dill-0.3.8 hyperpyyaml-1.2.2 multiprocess-0.70.16 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.5.82 nvidia-nvtx-cu12-12.1.105 pyarrow-17.0.0 requests-2.32.3 ruamel.yaml-0.18.6 ruamel.yaml.clib-0.2.8 speechbrain-1.0.0 xxhash-3.4.1\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!pip install git+https://github.com/huggingface/transformers.git" + ], + "metadata": { + "id": "HQCuMz3fwuHa", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "d1509a7b-505f-47db-aa74-9fb8341e787a" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Collecting git+https://github.com/huggingface/transformers.git\n", + " Cloning https://github.com/huggingface/transformers.git to /tmp/pip-req-build-m7fgjodb\n", + " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers.git /tmp/pip-req-build-m7fgjodb\n", + " Resolved https://github.com/huggingface/transformers.git to commit 96a074fa7e2c04b904f72d9e827398d4c5f90f25\n", + " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", + " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (3.15.4)\n", + "Requirement already satisfied: huggingface-hub<1.0,>=0.23.2 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (0.23.5)\n", + "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (1.25.2)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (24.1)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (6.0.1)\n", + "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (2024.5.15)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (2.32.3)\n", + "Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (0.19.1)\n", + "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (0.4.3)\n", + "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.0.dev0) (4.66.4)\n", + "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.23.2->transformers==4.43.0.dev0) (2023.6.0)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.23.2->transformers==4.43.0.dev0) (4.12.2)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.43.0.dev0) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.43.0.dev0) (3.7)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.43.0.dev0) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.43.0.dev0) (2024.7.4)\n", + "Building wheels for collected packages: transformers\n", + " Building wheel for transformers (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for transformers: filename=transformers-4.43.0.dev0-py3-none-any.whl size=9403605 sha256=c2505d30926e465339b5e53f7c1b7963724dddf757ce1523549bfbc390ce681b\n", + " Stored in directory: /tmp/pip-ephem-wheel-cache-b7r1edg2/wheels/e7/9c/5b/e1a9c8007c343041e61cc484433d512ea9274272e3fcbe7c16\n", + "Successfully built transformers\n", + "Installing collected packages: transformers\n", + " Attempting uninstall: transformers\n", + " Found existing installation: transformers 4.42.4\n", + " Uninstalling transformers-4.42.4:\n", + " Successfully uninstalled transformers-4.42.4\n", + "Successfully installed transformers-4.43.0.dev0\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!pip install --upgrade accelerate" + ], + "metadata": { + "id": "NfX4YNbs_HKP", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "414c91dc-0e2f-4cc4-a2e3-bc15af8f0bf8" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (0.32.1)\n", + "Requirement already satisfied: numpy<2.0.0,>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate) (1.25.2)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (24.1)\n", + "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n", + "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate) (6.0.1)\n", + "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.3.1+cu121)\n", + "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.23.5)\n", + "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.4.3)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.15.4)\n", + "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (4.12.2)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (1.13.0)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.3)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.4)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2023.6.0)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.20.5)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (12.1.105)\n", + "Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.3.1)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.0->accelerate) (12.5.82)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (2.32.3)\n", + "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (4.66.4)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.5)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.7)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2024.7.4)\n", + "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate) (1.3.0)\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "Do we have a GPU?" + ], + "metadata": { + "id": "g_Xffd7sRlpk" + } + }, + { + "cell_type": "code", + "source": [ + "!nvidia-smi" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "-XLi4c9DRnxA", + "outputId": "6d793249-e445-4b81-c0b7-8d14192bf4c8" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Mon Jul 22 19:12:49 2024 \n", + "+---------------------------------------------------------------------------------------+\n", + "| NVIDIA-SMI 535.104.05 Driver Version: 535.104.05 CUDA Version: 12.2 |\n", + "|-----------------------------------------+----------------------+----------------------+\n", + "| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |\n", + "| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |\n", + "| | | MIG M. |\n", + "|=========================================+======================+======================|\n", + "| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |\n", + "| N/A 48C P8 9W / 70W | 0MiB / 15360MiB | 0% Default |\n", + "| | | N/A |\n", + "+-----------------------------------------+----------------------+----------------------+\n", + " \n", + "+---------------------------------------------------------------------------------------+\n", + "| Processes: |\n", + "| GPU GI CI PID Type Process name GPU Memory |\n", + "| ID ID Usage |\n", + "|=======================================================================================|\n", + "| No running processes found |\n", + "+---------------------------------------------------------------------------------------+\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "In case no GPU is found, from the menu choose **Runtime > Change runtime type** and set **Hardware accelerator** to **GPU**. Then restart the runtime to activate the GPU." + ], + "metadata": { + "id": "bmdgnloAQPQ1" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Load the model\n", + "\n", + "We'll start from SpeechT5 that's already been fine-tuned for English TTS, and fine-tune it again but for a new language. For more info about the original checkpoint, you can find its model card on the [Hugging Face Hub](https://huggingface.co/microsoft/speecht5_tts)." + ], + "metadata": { + "id": "GB6Ur8DHuUy8" + } + }, + { + "cell_type": "code", + "source": [ + "from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech\n", + "\n", + "processor = SpeechT5Processor.from_pretrained(\"microsoft/speecht5_tts\")\n", + "model = SpeechT5ForTextToSpeech.from_pretrained(\"microsoft/speecht5_tts\")" + ], + "metadata": { + "id": "W7spxtTGtmba", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 365, + "referenced_widgets": [ + "5cd4197ba6cb43a79e8e48e3281d556a", + "37034519aba0437a89c974c344cc58be", + "69a2281cd24c473fa2f4874034bfe1bd", + "506636dde3f4495fa929c659ecf8b764", + "67fd8b2359ec4585a548b52f614531f1", + "c8be0944b2d14e47a2f7909138527aaf", + "11d479256d314d3eab585386482e318b", + "115279124c584e2daa48346a7c9c8e9c", + "350f730b810f4bd88740a77a7e0a51be", + "c16b239971bc41d8be09280b34536fd4", + "e92855e89e3e4ebba0159c6f24004aad", + "b89a27c225cf4e49860c8f62e32efaf6", + "fa94d043df65408a8418026350b837a1", + "169d1b4d3773401688dc1884d6532788", + "beb62f2bd7a24f9a82159ed016abb9b5", + "601c4fb9215444efb45f55852abd41d5", + "6bfda8329c3741f4a0f175d41603c707", + "877842a378c54836880b45d7b072c51b", + "fec3ab0d0be74c40a868ca3969e533c5", + "16951d20b1294e08b42339d08f97ae7b", + "91b3dc6e9a85404c96fd59cfb800d43f", + "b9290e687dcd420abfc46b43639fed28", + "64917c2ed79841e3a5080ffbe11baba8", + "976a925fc43c42f1a580fd808d32023d", + "9bf02a53411646439af4b7412d707923", + "fadd75cae7824fa598fd58ae994259ab", + "d7cd149116154f98aad430d857c46381", + "db176eb9bc144f5cbcacb0086d176571", + "fc0efaa60a504ffebb5e00bdc8c205b1", + "869df80d498642f4b3a1d1825372cef7", + "3518110403534f7f82a617d1bedc6315", + "e74722fed6a94c5bae623ed75c362a45", + "ec62796f2d86461ab698738058d21f82", + "f9735b84f4d3473a8307e736305cf252", + "0ba493d747144e1daac6252c6accc886", + "4138156fdfcf4d41947457d9670425df", + "eb350c3ec4bd4451b395c7fbd5f48f17", + "99d7ad89bdd346909213390a050f412f", + "9ecef1d0b473411b914eed7fa043478e", + "d827d96e5328476c80a212fad5570c78", + "22f4b0480fd34920b9a2e0c9d8c609dc", + "3f9e48a1f9014418825baa991e0f422c", + "cdb0d85e5dcb4d5998049b784acb00be", + "aaebe1f70f4f4d639d3ecbba9f406f8b", + "992902679da84067b429893c7870b816", + "af9cb18856474687a449ac515ede62e8", + "db44aadde79b40f1850078024e910183", + "f16031daae714a0181ddd0b31471f060", + "e7bdbfe7797a4b5db827f5b810d2d79b", + "a99df968c26040e3a9d8465d539b7844", + "45e7d7b493fb45d1b71b0f42464a9ac8", + "1eabe7caf021425a83295181e16a573d", + "e281d772babb4a2dbb1a949e6a5a440c", + "82d5d05b953042f4bc7ad53a122d6a03", + "786cb3e450de464fa04f9ed4fbe073e1", + "6c036b53916642e3993b40b66532f305", + "f02b5874bc1a4b29a0a8f65a455ae425", + "73bbb254a9f94a2f90776da888b551c2", + "4b400af9107d4cb09725a19a8978d33a", + "decda57cc9a7489fb32d384c270f4994", + "9b62f1cf2fe54ccda160abe4a281ca82", + "1073b875d7e040d1b96adc59ac722133", + "22f2f7b6cad948efa54f0c748d427777", + "ba3d74aab1d44f44a3b795f4e4a9177e", + "0a6f959beecf45f4ba2d1cb19f21a3bc", + "efd7335a34584dcab1c2ece372c23332", + "f093bd48a659437692d44be6308d0a53", + "140712a8dbb04cdd8dd7854cc1b579e5", + "980d09ee15b540a0868ed5e1cae7d867", + "616095ba34964997a82d5103681ec8fd", + "6d8d46c27f5e4d23a9170c06fb8e6947", + "1715e69a4fb84798b1d8d081991d0e65", + "bb212e00ea9b416db52167e0a64608ee", + "304787fbe0984b9f887fc948a8b888fc", + "e4138b99226846e9b4cfc4ea075329cd", + "f969b09762794b8f99ad8e2121945bc4", + "5348d94bb7114057bd7b3cb9885a0041" + ] + }, + "outputId": "0dc03789-0b00-4a88-b99c-40c395d2b8b2" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: \n", + "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", + "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n", + "You will be able to reuse this secret in all of your notebooks.\n", + "Please note that authentication is recommended but still optional to access public models or datasets.\n", + " warnings.warn(\n" + ] }, - "e10a5c2d674c4948978e0bc3fc2e8b0d": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_64eb31cf8d59468ea56a8e58c71d8122", - "placeholder": "​", - "style": "IPY_MODEL_0900daeba5cf4cb29d00a9c5ed5ad330", - "value": " 2.11k/2.11k [00:00<00:00, 31.4kB/s]" - } + { + "output_type": "display_data", + "data": { + "text/plain": [ + "preprocessor_config.json: 0%| | 0.00/433 [00:00=1.9 in /usr/local/lib/python3.10/dist-packages (from speechbrain==1.0.0) (2.3.1+cu121)\n", + "Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (from speechbrain==1.0.0) (2.3.1+cu121)\n", + "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from speechbrain==1.0.0) (4.66.4)\n", + "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from speechbrain==1.0.0) (0.23.5)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (3.15.4)\n", + "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (4.12.2)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (1.13.0)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (3.3)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (3.1.4)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (2023.6.0)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (2.20.5)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (12.1.105)\n", + "Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==1.0.0) (2.3.1)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.9->speechbrain==1.0.0) (12.5.82)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->speechbrain==1.0.0) (6.0.1)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->speechbrain==1.0.0) (2.32.3)\n", + "Requirement already satisfied: ruamel.yaml>=0.17.28 in /usr/local/lib/python3.10/dist-packages (from hyperpyyaml->speechbrain==1.0.0) (0.18.6)\n", + "Requirement already satisfied: ruamel.yaml.clib>=0.2.7 in /usr/local/lib/python3.10/dist-packages (from ruamel.yaml>=0.17.28->hyperpyyaml->speechbrain==1.0.0) (0.2.8)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.9->speechbrain==1.0.0) (2.1.5)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->speechbrain==1.0.0) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->speechbrain==1.0.0) (3.7)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->speechbrain==1.0.0) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->speechbrain==1.0.0) (2024.7.4)\n", + "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.9->speechbrain==1.0.0) (1.3.0)\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "import os\n", + "import torch\n", + "from speechbrain.inference.speaker import EncoderClassifier\n", + "\n", + "spk_model_name = \"speechbrain/spkrec-xvect-voxceleb\"\n", + "\n", + "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", + "speaker_model = EncoderClassifier.from_hparams(\n", + " source=spk_model_name,\n", + " run_opts={\"device\": device},\n", + " savedir=os.path.join(\"/tmp\", spk_model_name)\n", + ")\n", + "\n", + "def create_speaker_embedding(waveform):\n", + " with torch.no_grad():\n", + " speaker_embeddings = speaker_model.encode_batch(torch.tensor(waveform))\n", + " speaker_embeddings = torch.nn.functional.normalize(speaker_embeddings, dim=2)\n", + " speaker_embeddings = speaker_embeddings.squeeze().cpu().numpy()\n", + " return speaker_embeddings" + ], + "metadata": { + "id": "smJs3_VB1Da2", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 177, + "referenced_widgets": [ + "d8e8d1b0adcd4d47b061aad1486604cb", + "1f15ee66a1f24e41b5630d5616243a7b", + "651b513c24e24a5990591f95f24a4c0a", + "708e0de686af4966a72d66fb174c1cfa", + "f46eb3dacc954c729a2c2b44d91a5382", + "db9886b3bdf24a7690e5464275656dca", + "5c7aa125de6544cf9ff580cceb311c9e", + "f0297cf643064c4c97df2e0749207379", + "caaca6fb45eb453dbd2d8bb4ff5d3d52", + "c78ec4ad3bfb443982281085989394fe", + "032cf630889f4f599dad2a0f718dd63e", + "59b8375db47b41709137a8831f06a693", + "969bec5ee95248d4a948965c74ff3311", + "8f604dc7fccf4572821cb040ab5d8c5c", + "677cfd9f2d3f4f669e488d12d21b8e20", + "974b89e5205a4487acb8577df5ea85e6", + "3e0e63681dfe4201ae9d8b7a370fca52", + "630aa4eac24e481a9fdb9d999f0c8822", + "6b988b31851c4db6890479404c7011cf", + "27b0e9d94b0a4d8cac920df223606d10", + "9d8b343299174f5789bfef21e23cfff6", + "8c299f76bb244a748838b967e5d93c2f", + "1fff9026fa29474ca2b652a2e0e98235", + "eebdffbf80d542a0bdea7e2e4f66fbe8", + "7827a86376c94da99efb90f5842864ed", + "d8c83b57302a458aa3ee71cac9632455", + "08a04116a15043e88c1c50b76bc3a77b", + "e1f400ffbb124a56a281832bcc54eaf9", + "a3ef8ad842a346df9ffc0f31725c9606", + "fa605877967d4109a4fd496e63e663ca", + "c1cb1e279bdd4de0a725dd51a8489563", + "37f6208a83084b92a458e21c197cad3f", + "1e1213f764474d7bbd426a5327829eb9", + "5492a2c2d56844bdabc9aaaab9bdc35f", + "669272db738947e2b8102102a57bc87a", + "dad194753c8e439c9d62285c0c06546a", + "ae2f4d6301694356b5878fab0de3ea83", + "156fa699696c4e26b2842e89954d202b", + "b0cda3f2c228491bb6ce981267141f52", + "3fb43042ede944c485c1eadf21ebfa96", + "7eecca112ead43c9ab55a5220122ce97", + "5f90e9766c3b44f0bded6715e12682d5", + "b01b07d8119c4485ab5844ce7351aad8", + "bb435b975d2844879538ba5b00c377b5", + "1c0c9d45f86f4945965a4784109020ff", + "8462433da1b847b09f137a5017b575c8", + "6535f9ad0436497dbcec30c1df342ac9", + "4d02d845fa034829900635be82eb64ad", + "6d274c81d3ed486a90598cee551db717", + "b58864d3bfb7426995ef989334687286", + "04512216d85b42c4ae02d3f1083acbe9", + "10aea82371aa4b23bb1e2f906778f92e", + "935177cdab4a419ebb327a9641c2a6ff", + "a10a271823244bce91dbc042bf838746", + "265bbe545b99430f85aa5884b64ac014" + ] }, - "ea8fbaa445bd442b82bb60a67b0efcea": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } + "outputId": "b8c498cb-603a-4761-8f16-849cb8d1ca49" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "hyperparams.yaml: 0%| | 0.00/2.04k [00:00` to mark the end of the sentence." + ], + "metadata": { + "id": "nvNI_JrE2oA8" + } + }, + { + "cell_type": "code", + "source": [ + "tokenizer.decode(processed_example[\"input_ids\"])" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 35 }, - "efd7335a34584dcab1c2ece372c23332": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } + "id": "uu8PgZqH07lW", + "outputId": "9559a4fa-c992-4971-f5be-201d41e77335" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "'kash yh wqt kbhy nh gzre.'" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 17 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "Speaker embeddings should be a 512-element vector:" + ], + "metadata": { + "id": "wOdMw-xa2u_8" + } + }, + { + "cell_type": "code", + "source": [ + "processed_example[\"speaker_embeddings\"].shape" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, - "efedd4a0d92a4a9497276de827370261": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } + "id": "uuybSBq32AuH", + "outputId": "de2838f0-c816-48df-d28d-dcd72a800d6f" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "(512,)" + ] + }, + "metadata": {}, + "execution_count": 18 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "The labels should be a log-mel spectrogram with 80 mel bins." + ], + "metadata": { + "id": "YzyoPE2y2zHk" + } + }, + { + "cell_type": "code", + "source": [ + "import matplotlib.pyplot as plt\n", + "plt.figure()\n", + "plt.imshow(processed_example[\"labels\"].T)\n", + "plt.show()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 216 }, - "efeef3aa079d4bf4bc4c5049f9c74e16": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } + "id": "dKu2km552GL-", + "outputId": "6498e8bd-a15f-49c3-996e-f1f9c31c25c2" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "\n", + "If we run a vocoder on the log-mel spectrogram, it should produce the original audio again. We'll load the HiFi-GAN vocoder from the original [SpeechT5 checkpoint](https://hf.co/microsoft/speecht5_hifigan)." + ], + "metadata": { + "id": "bWMT9X6w237M" + } + }, + { + "cell_type": "code", + "source": [ + "from transformers import SpeechT5HifiGan\n", + "vocoder = SpeechT5HifiGan.from_pretrained(\"microsoft/speecht5_hifigan\")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 81, + "referenced_widgets": [ + "a60987317acd40278489533a2d9dd021", + "c9662066695c43e7901ba019a0dc9e8c", + "4ca762251949444f921863535a18e5c5", + "d7142a382f884564921bcfcf65909287", + "13226fa6805041fdb7e3976e4577a66e", + "7c992442c78045e0962299728b49bbb5", + "a5fe768b739d4df896d15370e981b656", + "4a7bd718c8874fc2bbd7a566e1da124d", + "ea8fbaa445bd442b82bb60a67b0efcea", + "db1394f796f84b5295e16f1f8b2a526a", + "f44278459f804c7e9412f72c8cb4eef0", + "33e739de4df54f96a276027d2d1f66ea", + "2d3eb78c7b994f3cb2d57d80458c35d6", + "de8ee1e97a0f4bbfa17281a0c067b5b1", + "5ab5b7305633479494e991c26c2268a9", + "ab27bce16ed24effbddb7596ffe2c3c1", + "5d30def7a2bb463baa858eb0eee9d094", + "06508d700e9c426b85f374381d3439d9", + "af4aeb90cfbc4937860ffd47ef7987e5", + "8b5abf1e77284e549e1ed7cdd100e2af", + "e550d62c5fb54e8c9be548e252a4ddc3", + "b51084470848412d9360ed3487aaf3f6" + ] }, - "f0297cf643064c4c97df2e0749207379": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } + "id": "2Yu-rqwa1zns", + "outputId": "3b909915-c86b-4ee3-d2bb-12b1d2b2ede6" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "config.json: 0%| | 0.00/636 [00:00" + ], + "text/html": [ + "\n", + " \n", + " " + ] + }, + "metadata": {}, + "execution_count": 22 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "That all looks and sounds good! We can now process the entire dataset. This can take between 5 and 10 minutes." + ], + "metadata": { + "id": "RPLVad8w3CvV" + } + }, + { + "cell_type": "code", + "source": [ + "dataset = dataset.map(\n", + " prepare_dataset, remove_columns=dataset.column_names,\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 86, + "referenced_widgets": [ + "2ebee62340c24076b6edeb96d233b5e0", + "dc0e721504184b778486802d47239e00", + "4744d62b21e645b8bad84578aed387d3", + "ef635c73df96463ea145fad659b04028", + "00adec96a5654f3a9d08c8331366f704", + "3fd3b45e98ff4292a1444f89fc6ae95e", + "876341d2a2484e60a72caad3dc02c1b4", + "4699dc096aa644b6add210252efa7334", + "f2f329976e13413c9bcef0e56280d563", + "bd10c6180edc414f877b5ac363801a42", + "b818deafc75f4bfa8139ae6192dab50d" + ] + }, + "id": "ekis02SC2hBN", + "outputId": "dab33b54-b3a0-43fe-b624-aab4ec391873" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Map: 0%| | 0/4112 [00:00 600). Running this sequence through the model will result in indexing errors\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "Some of the examples in the dataset are apparently longer than the maximum input length the model can handle (600 tokens), so we should remove those from the dataset. In fact, to allow for larger batch sizes we'll remove anything over 200 tokens." + ], + "metadata": { + "id": "7z_QGJ1u3LTa" + } + }, + { + "cell_type": "code", + "source": [ + "def is_not_too_long(input_ids):\n", + " input_length = len(input_ids)\n", + " return input_length < 200\n", + "\n", + "dataset = dataset.filter(is_not_too_long, input_columns=[\"input_ids\"])" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 49, + "referenced_widgets": [ + "2993094c7ff6425eab9bb0b1bdf1d7ac", + "fd6cb6748b1a4d83bbd3c1f9bc9293c9", + "a15ad78eb7e249a2ae8f1a4e0b0e359e", + "39f6a7a3035a4c53bebc34e7a90ad14c", + "078823ec9ed64a58abc1ee0a7d55976a", + "b710b2c93fcb437eb220dbd57ba1a235", + "4acb801fd07e4e1db048921d83fad83f", + "3bd4aa82001248acb3758f0ff98fe64c", + "494b73ce426e44da9601305d859f484c", + "c350945401cb48968758c0674598a855", + "0194367f515647b1ae5bc638d212c2ce" + ] + }, + "id": "Sy4kcOco3Ks3", + "outputId": "516034d9-6b6f-44ff-d18a-452e18dff79d" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Filter: 0%| | 0/4112 [00:00 Dict[str, torch.Tensor]:\n", + "\n", + " input_ids = [{\"input_ids\": feature[\"input_ids\"]} for feature in features]\n", + " label_features = [{\"input_values\": feature[\"labels\"]} for feature in features]\n", + " speaker_features = [feature[\"speaker_embeddings\"] for feature in features]\n", + "\n", + " # collate the inputs and targets into a batch\n", + " batch = processor.pad(\n", + " input_ids=input_ids,\n", + " labels=label_features,\n", + " return_tensors=\"pt\",\n", + " )\n", + "\n", + " # replace padding with -100 to ignore loss correctly\n", + " batch[\"labels\"] = batch[\"labels\"].masked_fill(\n", + " batch.decoder_attention_mask.unsqueeze(-1).ne(1), -100\n", + " )\n", + "\n", + " # not used during fine-tuning\n", + " del batch[\"decoder_attention_mask\"]\n", + "\n", + " # round down target lengths to multiple of reduction factor\n", + " if model.config.reduction_factor > 1:\n", + " target_lengths = torch.tensor([\n", + " len(feature[\"input_values\"]) for feature in label_features\n", + " ])\n", + " target_lengths = target_lengths.new([\n", + " length - length % model.config.reduction_factor for length in target_lengths\n", + " ])\n", + " max_length = max(target_lengths)\n", + " batch[\"labels\"] = batch[\"labels\"][:, :max_length]\n", + "\n", + " # also add in the speaker embeddings\n", + " batch[\"speaker_embeddings\"] = torch.tensor(speaker_features)\n", + "\n", + " return batch" + ], + "metadata": { + "id": "rZOX8bTe3Kq5" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "In SpeechT5, the input to the decoder part of the model is reduced by a factor 2. In other words, it throws away every other timestep from the target sequence. The decoder then predicts a sequence that is twice as long. Since the original target sequence length may be odd, the data collator makes sure to round the maximum length of the batch down to be a multiple of 2." + ], + "metadata": { + "id": "ffNanldmrlbD" + } + }, + { + "cell_type": "code", + "source": [ + "data_collator = TTSDataCollatorWithPadding(processor=processor)" + ], + "metadata": { + "id": "CJKY4DVO4khr" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "Let's test the data collator." + ], + "metadata": { + "id": "McZfpBzL4mRK" + } + }, + { + "cell_type": "code", + "source": [ + "features = [\n", + " dataset[\"train\"][0],\n", + " dataset[\"train\"][1],\n", + " dataset[\"train\"][20],\n", + "]\n", + "\n", + "batch = data_collator(features)" + ], + "metadata": { + "id": "78-XVnD04ouJ" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "{k:v.shape for k,v in batch.items()}" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, - "f1e85d48269a4675aa3eb1484d5ebbf7": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "LabelModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "LabelModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "LabelView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_a903a041f8f34e95b7eb95e7680e68af", - "placeholder": "​", - "style": "IPY_MODEL_499ae3562b0e4636a5526230245d502a", - "value": "Your token has been saved to /root/.cache/huggingface/token" - } + "id": "vuWoBSpW4pY9", + "outputId": "cfaf09be-cef4-4328-f96d-8c3eda7ec71a" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "{'input_ids': torch.Size([3, 106]),\n", + " 'attention_mask': torch.Size([3, 106]),\n", + " 'labels': torch.Size([3, 580, 80]),\n", + " 'speaker_embeddings': torch.Size([3, 512])}" + ] + }, + "metadata": {}, + "execution_count": 31 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "Looks good!" + ], + "metadata": { + "id": "sVMpz-tpP-vw" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Training" + ], + "metadata": { + "id": "_iOqGsqq4uJv" + } + }, + { + "cell_type": "markdown", + "source": [ + "It's always a good idea to upload model checkpoints directly to the [Hugging Face Hub](https://huggingface.co/) while training. To allow this, first log in to the Hub by entering your Hub authentication token:" + ], + "metadata": { + "id": "uQiZlXN9ICmc" + } + }, + { + "cell_type": "code", + "source": [ + "from huggingface_hub import notebook_login\n", + "\n", + "notebook_login()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 145, + "referenced_widgets": [ + "9defb63d40414377962be7a45fe04863", + "4bdb55d30a0b4b648c082f2cf5921383", + "b9d136e1b7944a08a3b206be697e8bcd", + "9a84e7b2ed2e4854b3a27c4a7a6d7b29", + "17f05d9f756e466eba646e8dca6a89e3", + "9d901610487e4d7389072038d0e5d72d", + "8e0bf7d4611641c091e87fbacbf10a19", + "c4660f3058d14daba1940d89e200b65d", + "31ed87b6e80b4822b430c51ae043edcf", + "4edcc714fca4485190e973ed83325af1", + "8c8333ae0d3d4ba7813d4d91245823db", + "7dc5299d9e264f4d9dda9ff552d5d5cc", + "034918f3b833496397f34caa9a0bfbb4", + "0a595220c4004b6ca316c47babe4e5a7", + "1e34bc54a39b42b1a5a2ece20823ca3f", + "efeef3aa079d4bf4bc4c5049f9c74e16", + "821bc686077d4d4faf73a98e60ef2262", + "e6a2cb79b3a14ceb96e44b93529a1b17", + "18f235d673c1422abc9a7a897295aaf4", + "e87df5c1d1fb4d19bd7e8663f39a9073", + "346edbb27fec4479ad74331561fe6d4f", + "382582721b924a77a6ed9ebf2d0e78c6", + "f1e85d48269a4675aa3eb1484d5ebbf7", + "bd810380dabe446d874fbcdbf0a2a815", + "5942dd51d8014d32a6400698fa84f88e", + "813e7e5696b84a0091524b551d94b1a6", + "59f995c679f843eba17be9f2cab2b5ca", + "aa7bf7b3cc7441888151beffb6d30321", + "a903a041f8f34e95b7eb95e7680e68af", + "499ae3562b0e4636a5526230245d502a", + "c5b791315d534952b9087a66d94a49a4", + "d3d5fd89f4df4f278529a4d959f64d5f" + ] }, - "f22ab8b84c9a406d9383a1253576cf62": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_fe75e4e2a67749b49efe29817c9148db", - "placeholder": "​", - "style": "IPY_MODEL_1660e3387e094116b87f3a8f04782124", - "value": " 101k/101k [00:00<00:00, 135kB/s]" - } + "id": "1z3DEgUOIBz7", + "outputId": "ade902b9-4eda-4a99-fd24-3f62259bf680" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "VBox(children=(HTML(value='
\n", + " \n", + " \n", + " [ 2353/10500 41:28 < 2:23:44, 0.94 it/s, Epoch 20.28/91]\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
StepTraining LossValidation Loss
5000.5782000.507094
10000.5248000.486292
15000.5125000.474619
20000.5081000.472668

" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" }, - "f969b09762794b8f99ad8e2121945bc4": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } + { + "metadata": { + "tags": null + }, + "name": "stderr", + "output_type": "stream", + "text": [ + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n" + ] }, - "f9735b84f4d3473a8307e736305cf252": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_0ba493d747144e1daac6252c6accc886", - "IPY_MODEL_4138156fdfcf4d41947457d9670425df", - "IPY_MODEL_eb350c3ec4bd4451b395c7fbd5f48f17" + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" ], - "layout": "IPY_MODEL_99d7ad89bdd346909213390a050f412f" - } + "text/html": [ + "\n", + "

\n", + " \n", + " \n", + " [10500/10500 3:07:45, Epoch 90/91]\n", + "
\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
StepTraining LossValidation Loss
5000.5782000.507094
10000.5248000.486292
15000.5125000.474619
20000.5081000.472668
25000.4967000.468271
30000.4905000.464520
35000.4794000.466818
40000.4829000.464720
45000.4770000.464455
50000.4637000.470984
55000.4743000.468265
60000.4595000.469457
65000.4735000.468382
70000.4613000.472399
75000.4678000.473160
80000.4538000.472332
85000.4536000.474660
90000.4587000.473995
95000.4536000.476193
100000.4606000.476838
105000.4528000.479585

" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n", + "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "TrainOutput(global_step=10500, training_loss=0.4873873142969041, metrics={'train_runtime': 11266.2505, 'train_samples_per_second': 29.824, 'train_steps_per_second': 0.932, 'total_flos': 2.251261023307164e+16, 'train_loss': 0.4873873142969041, 'epoch': 90.51724137931035})" + ] + }, + "metadata": {}, + "execution_count": 42 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "If we do one more `push_to_hub()` after training we can get a nice model card built for us. We simply have to set the appropriate keyword arguments (kwargs). You can change these values to match your dataset, language and model name accordingly:" + ], + "metadata": { + "id": "4z3CzVGSs000" + } + }, + { + "cell_type": "code", + "source": [ + "kwargs = {\n", + " \"dataset_tags\": \"m-aliabbas/common_voice_urdu1\",\n", + " \"dataset\": \"common_voice_urdu1\", # a 'pretty' name for the training dataset\n", + " \"dataset_args\": \"split: train\",\n", + " \"model_name\": \"SpeechT5 TTS urdu\", # a 'pretty' name for your model\n", + " \"finetuned_from\": \"microsoft/speecht5_tts\",\n", + " \"tasks\": \"text-to-speech\",\n", + "}\n" + ], + "metadata": { + "id": "NpXOJAZIs2-n" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "The training results can now be uploaded to the Hub. To do so, execute the `push_to_hub` command:" + ], + "metadata": { + "id": "ooEluBcXs5hJ" + } + }, + { + "cell_type": "code", + "source": [ + "trainer.push_to_hub(**kwargs)" + ], + "metadata": { + "id": "mpodV89js9KT", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 156, + "referenced_widgets": [ + "456aa13fa38c4c01b9f43570e31556fe", + "ec7ac27d32c44b40ac8fd18a7700962d", + "fbeb5a0f2394434fb67644f452dcb6b2", + "f22ab8b84c9a406d9383a1253576cf62", + "3915aa47172546afb3f09ea1f7c5b947", + "308b5dd72e6f4ea39d9be4c2e4a02512", + "9aa2c30314774289a458d92cabf2e9e1", + "4d5bdff9982e40138888bc9c72f9233e", + "2c9002098b114841b511b97c5fa39f14", + "fe75e4e2a67749b49efe29817c9148db", + "1660e3387e094116b87f3a8f04782124" + ] }, - "fa605877967d4109a4fd496e63e663ca": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } + "outputId": "ecfd3656-aacf-4f48-f2bc-718285ecdcc6" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.\n", + "Non-default generation parameters: {'max_length': 1876}\n", + "Your generation config was originally created from the model config, but the model config has changed since then. Unless you pass the `generation_config` argument to this model's `generate` calls, they will revert to the legacy behavior where the base `generate` parameterization is loaded from the model config instead. To avoid this behavior and this warning, we recommend you to overwrite the generation config model attribute before calling the model's `save_pretrained`, preferably also removing any generation kwargs from the model config. This warning will be raised to an exception in v4.41.\n" + ] }, - "fa94d043df65408a8418026350b837a1": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_6bfda8329c3741f4a0f175d41603c707", - "placeholder": "​", - "style": "IPY_MODEL_877842a378c54836880b45d7b072c51b", - "value": "tokenizer_config.json: 100%" - } + { + "output_type": "display_data", + "data": { + "text/plain": [ + "events.out.tfevents.1721676197.d34fde1d2e44.268.2: 0%| | 0.00/101k [00:00\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_pretrained\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_pretrained\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"your_model_save_directory\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py\u001b[0m in \u001b[0;36msave_pretrained\u001b[0;34m(self, save_directory, is_main_process, state_dict, save_function, push_to_hub, max_shard_size, safe_serialization, variant, token, save_peft_format, **kwargs)\u001b[0m\n\u001b[1;32m 2476\u001b[0m \u001b[0;32mreturn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2477\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2478\u001b[0;31m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmakedirs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msave_directory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexist_ok\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2479\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2480\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mpush_to_hub\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/lib/python3.10/os.py\u001b[0m in \u001b[0;36mmakedirs\u001b[0;34m(name, mode, exist_ok)\u001b[0m\n\u001b[1;32m 223\u001b[0m \u001b[0;32mreturn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 224\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 225\u001b[0;31m \u001b[0mmkdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 226\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mOSError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 227\u001b[0m \u001b[0;31m# Cannot rely on checking for EEXIST, since the operating system\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: ''" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "You can now share this model with anyone using the link on the Hub." + ], + "metadata": { + "id": "ojrUgMeEs_LP" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Evaluate" + ], + "metadata": { + "id": "5K1AQd8B7b-p" + } + }, + { + "cell_type": "markdown", + "source": [ + "After training finishes, let's use the model to synthesize some speech!\n", + "\n", + "I'm loading the model from the Hugging Face Hub, as the Colab notebook was terminated before training finished (which is why it's a good idea to use `push_to_hub=True` when training)." + ], + "metadata": { + "id": "TrqUYy3-Qr1w" + } + }, + { + "cell_type": "code", + "source": [ + "model= SpeechT5ForTextToSpeech.from_pretrained(\"pocketmonkey/speecht5_tts_urdu\")" + ], + "metadata": { + "id": "bos-fW6CHijQ", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 113, + "referenced_widgets": [ + "af584652d0304a899e66314d61726323", + "3b74fdd0043949548e50b1d87413505b", + "958d0637ccad4af49815a2d137fee333", + "e10a5c2d674c4948978e0bc3fc2e8b0d", + "68a15f79b7ab42eaa0b14086f2b54ed6", + "6916935a59f94d6e95449be55732c80c", + "cef8c2e1224b4f0eb21e4963d53431b5", + "7597054472514485afa120d6266c91a5", + "6035b946f770456fbfd123adbb5e3be9", + "64eb31cf8d59468ea56a8e58c71d8122", + "0900daeba5cf4cb29d00a9c5ed5ad330", + "054b003700514935960c7ee0895b8c8e", + "2dcbcbfcbb3c455a8beee0d7f4c12c05", + "be44a4398328449daebb6bd48e2519f7", + "bcd4e9d178c944f6973b2d62fa1e5538", + "d8419ef35db5403c862e8321572ad376", + "af01cdbb16dd490984a749d2da6eff34", + "54783e715ad0408eaa512f7d28a374b2", + "d0f6e0eefec74d9aa2a0a00868c77a55", + "bd858f248a124f14833b044f7b0b71e5", + "d432e91ec63b4655a50bc775ee74aab4", + "af1e15c4f52e4ea5886d1631de2fbe39", + "a617fca4345c4d21a6c44d5ef8246f91", + "3109d5c2ffe04d5ebf296cc26a334a38", + "4d97d63c12ab4c37b53207cf91ac9794", + "a3f2bf1d001c4f2d8571d2a4db8972d1", + "e27fcac6c1be4ecc89028aa8368e6e89", + "c1b4ea7cfc0d434dbb68027af48a5f07", + "5e1fd59b51d1459da614ab5d51116d59", + "ced524c3f07b40e792db0bf1e9c3fe92", + "b257195cf3314cb4bc3aeddc4da142b9", + "95446dc9a4cc46469d1efa27c7896bfc", + "3cd2ea08c82e49a08396e31dfead7f6f" + ] }, - "fc0efaa60a504ffebb5e00bdc8c205b1": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } + "outputId": "ad9f4982-f54c-4faa-c710-f3f7df98d480" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "config.json: 0%| | 0.00/2.11k [00:00" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "Finally, use the vocoder to turn the spectrogram into sound." + ], + "metadata": { + "id": "McG3EnpYRJVj" + } + }, + { + "cell_type": "code", + "source": [ + "with torch.no_grad():\n", + " speech = vocoder(spectrogram)" + ], + "metadata": { + "id": "MpogdOe_7uoe" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "from IPython.display import Audio\n", + "Audio(speech.numpy(), rate=16000)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 75 }, - "fec3ab0d0be74c40a868ca3969e533c5": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } + "id": "5H_FaVuW7wXt", + "outputId": "ce585e70-1e90-4cf5-af17-9ac311dee7ee" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "\n", + " \n", + " " + ] + }, + "metadata": {}, + "execution_count": 61 + } + ] + }, + { + "cell_type": "code", + "source": [ + "import soundfile as sf\n", + "sf.write(\"output.wav\", speech.numpy(), samplerate=16000)" + ], + "metadata": { + "id": "PV0nUOmO7xvv", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 183 + }, + "outputId": "3e0c913d-86ac-41e6-dba1-144238fa147d" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "error", + "ename": "TypeError", + "evalue": "can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msoundfile\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0msf\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0msf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"output.wav\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mspeech\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnumpy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msamplerate\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m16000\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;31mTypeError\u001b[0m: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first." + ] } + ] + }, + { + "cell_type": "markdown", + "source": [], + "metadata": { + "id": "fiir-kCPYa60" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Building a demo\n", + "\n", + "To showcase your newly fine-tuned model, make a demo on Hugging Face Spaces! We've created a [template Gradio demo](https://huggingface.co/spaces/Matthijs/speecht5-tts-demo) that you can easily copy and make your own.\n", + "\n", + "Click the link to duplicate the template demo to your account: https://huggingface.co/spaces/Matthijs/speecht5-tts-demo?duplicate=true (or from the three-dot button at the top choose **Duplicate this Space**).\n", + "\n", + "We recommend giving your space a similar name to your fine-tuned model (e.g. `speecht5_tts_voxpopuli_nl`) and setting the visibility to \"Public\".\n", + "\n", + "Once you've duplicated the Space to your account, click **Files and versions > app.py > edit**. Change the model identifier to your fine-tuned model (line 9). Scroll to the bottom of the page and click **Commit changes to main**. The demo will reboot, this time using your fine-tuned model.\n", + "\n", + "You can share this demo with your friends and family so that they can use the model that you've trained!" + ], + "metadata": { + "id": "wm7B3zxrumfF" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Conclusion\n", + "\n", + "That's it, you've fine-tuned SpeechT5 for TTS on a custom dataset!\n", + "\n", + "In our experience, it can be difficult to get good results out of this model. The results can be rather noisy and sometimes what the model outputs doesn't even sound like speech at all. A lot of this appears to be related to the speaker embeddings. Since SpeechT5 was pre-trained with English x-vectors, it gives the best results using those English speaker embeddings. So if the generated speech sounds bad, try using a different speaker embedding and it might improve.\n", + "\n", + "Of course, the demo above was only trained for 3000 iterations. Training for longer should improve the results. Even so, the speech clearly is Dutch instead of English, and it does capture the voice characteristics of the speaker (compare to the original audio in the example).\n", + "\n", + "Another thing to experiment with is the model's configuration. For example, try using `config.reduction_factor = 1` to see if this improves the results." + ], + "metadata": { + "id": "W5_p2oWERU3C" + } + }, + { + "cell_type": "markdown", + "source": [ + "A final note on ethical concerns: While TTS technology has many beneficial uses, it can also be used for nefarious purposes such as imitating someone's voice without their permission. Please use TTS wisely and responsibly!" + ], + "metadata": { + "id": "58ISNvOwuGiY" } + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "L-1ph4naugf6" + }, + "execution_count": null, + "outputs": [] } - }, - "nbformat": 4, - "nbformat_minor": 0 -} + ] +} \ No newline at end of file