![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from google.colab import drive\n",
+ "drive.mount('/content/drive')"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "iJ7lF3nt0FrJ",
+ "outputId": "9687f03a-9f1b-4a20-dae7-936d772251bf"
+ },
+ "execution_count": 1,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Mounted at /content/drive\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "oftAT2g8zkhU",
+ "outputId": "4eb210a7-4d25-4a45-a8a4-b0aafe146a8d"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.44.2)\n",
+ "Collecting datasets\n",
+ " Downloading datasets-3.0.2-py3-none-any.whl.metadata (20 kB)\n",
+ "Requirement already satisfied: soundfile in /usr/local/lib/python3.10/dist-packages (0.12.1)\n",
+ "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (0.34.2)\n",
+ "Collecting speechbrain==0.5.16\n",
+ " Downloading speechbrain-0.5.16-py3-none-any.whl.metadata (23 kB)\n",
+ "Collecting hyperpyyaml (from speechbrain==0.5.16)\n",
+ " Downloading HyperPyYAML-1.2.2-py3-none-any.whl.metadata (7.6 kB)\n",
+ "Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from speechbrain==0.5.16) (1.4.2)\n",
+ "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from speechbrain==0.5.16) (1.26.4)\n",
+ "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from speechbrain==0.5.16) (24.1)\n",
+ "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from speechbrain==0.5.16) (1.13.1)\n",
+ "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from speechbrain==0.5.16) (0.2.0)\n",
+ "Requirement already satisfied: torch>=1.9 in /usr/local/lib/python3.10/dist-packages (from speechbrain==0.5.16) (2.5.0+cu121)\n",
+ "Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (from speechbrain==0.5.16) (2.5.0+cu121)\n",
+ "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from speechbrain==0.5.16) (4.66.5)\n",
+ "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from speechbrain==0.5.16) (0.24.7)\n",
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.16.1)\n",
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.2)\n",
+ "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2024.9.11)\n",
+ "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.32.3)\n",
+ "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.5)\n",
+ "Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.19.1)\n",
+ "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (16.1.0)\n",
+ "Collecting dill<0.3.9,>=0.3.0 (from datasets)\n",
+ " Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n",
+ "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.2.2)\n",
+ "Collecting xxhash (from datasets)\n",
+ " Downloading xxhash-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
+ "Collecting multiprocess<0.70.17 (from datasets)\n",
+ " Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)\n",
+ "Requirement already satisfied: fsspec<=2024.9.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from fsspec[http]<=2024.9.0,>=2023.1.0->datasets) (2024.6.1)\n",
+ "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.10.10)\n",
+ "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.10/dist-packages (from soundfile) (1.17.1)\n",
+ "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n",
+ "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0->soundfile) (2.22)\n",
+ "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (2.4.3)\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) (24.2.0)\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) (6.1.0)\n",
+ "Requirement already satisfied: yarl<2.0,>=1.12.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.16.0)\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->speechbrain==0.5.16) (4.12.2)\n",
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.4.0)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.10)\n",
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.2.3)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.8.30)\n",
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==0.5.16) (3.4.2)\n",
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==0.5.16) (3.1.4)\n",
+ "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9->speechbrain==0.5.16) (1.13.1)\n",
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy==1.13.1->torch>=1.9->speechbrain==0.5.16) (1.3.0)\n",
+ "Collecting ruamel.yaml>=0.17.28 (from hyperpyyaml->speechbrain==0.5.16)\n",
+ " Downloading ruamel.yaml-0.18.6-py3-none-any.whl.metadata (23 kB)\n",
+ "Requirement 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) (2024.2)\n",
+ "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.2)\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==0.5.16)\n",
+ " Downloading ruamel.yaml.clib-0.2.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.7 kB)\n",
+ "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.10/dist-packages (from yarl<2.0,>=1.12.0->aiohttp->datasets) (0.2.0)\n",
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.9->speechbrain==0.5.16) (3.0.2)\n",
+ "Downloading speechbrain-0.5.16-py3-none-any.whl (630 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m630.6/630.6 kB\u001b[0m \u001b[31m19.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading datasets-3.0.2-py3-none-any.whl (472 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m472.7/472.7 kB\u001b[0m \u001b[31m22.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading 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[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading 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[31m11.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading HyperPyYAML-1.2.2-py3-none-any.whl (16 kB)\n",
+ "Downloading xxhash-3.5.0-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[31m18.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading 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[31m10.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading ruamel.yaml.clib-0.2.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (722 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m722.2/722.2 kB\u001b[0m \u001b[31m48.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hInstalling collected packages: xxhash, ruamel.yaml.clib, dill, ruamel.yaml, multiprocess, hyperpyyaml, speechbrain, datasets\n",
+ "Successfully installed datasets-3.0.2 dill-0.3.8 hyperpyyaml-1.2.2 multiprocess-0.70.16 ruamel.yaml-0.18.6 ruamel.yaml.clib-0.2.12 speechbrain-0.5.16 xxhash-3.5.0\n"
+ ]
+ }
+ ],
+ "source": [
+ "!pip install transformers datasets soundfile accelerate speechbrain==0.5.16"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install git+https://github.com/huggingface/transformers.git"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "8w0PTXCO0ik3",
+ "outputId": "ca41f6a3-08bd-4242-d78d-faf56ed979b5"
+ },
+ "execution_count": 3,
+ "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-dzo_7ae9\n",
+ " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers.git /tmp/pip-req-build-dzo_7ae9\n",
+ " Resolved https://github.com/huggingface/transformers.git to commit e50bf61decf741c6d59e4ba633b7392712673bda\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==4.46.0.dev0) (3.16.1)\n",
+ "Requirement already satisfied: huggingface-hub<1.0,>=0.23.2 in /usr/local/lib/python3.10/dist-packages (from transformers==4.46.0.dev0) (0.24.7)\n",
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.46.0.dev0) (1.26.4)\n",
+ "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.46.0.dev0) (24.1)\n",
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.46.0.dev0) (6.0.2)\n",
+ "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.46.0.dev0) (2024.9.11)\n",
+ "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers==4.46.0.dev0) (2.32.3)\n",
+ "Collecting tokenizers<0.21,>=0.20 (from transformers==4.46.0.dev0)\n",
+ " Downloading tokenizers-0.20.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
+ "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.46.0.dev0) (0.4.5)\n",
+ "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers==4.46.0.dev0) (4.66.5)\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==4.46.0.dev0) (2024.6.1)\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==4.46.0.dev0) (4.12.2)\n",
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.46.0.dev0) (3.4.0)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.46.0.dev0) (3.10)\n",
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.46.0.dev0) (2.2.3)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.46.0.dev0) (2024.8.30)\n",
+ "Downloading tokenizers-0.20.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.0 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m35.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hBuilding wheels for collected packages: transformers\n",
+ " Building wheel for transformers (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+ " Created wheel for transformers: filename=transformers-4.46.0.dev0-py3-none-any.whl size=10025577 sha256=3ea337cf25b375b36eb8c60ce90b74a21a9825afaf9417674e4193c178527de9\n",
+ " Stored in directory: /tmp/pip-ephem-wheel-cache-1tboskg1/wheels/e7/9c/5b/e1a9c8007c343041e61cc484433d512ea9274272e3fcbe7c16\n",
+ "Successfully built transformers\n",
+ "Installing collected packages: tokenizers, transformers\n",
+ " Attempting uninstall: tokenizers\n",
+ " Found existing installation: tokenizers 0.19.1\n",
+ " Uninstalling tokenizers-0.19.1:\n",
+ " Successfully uninstalled tokenizers-0.19.1\n",
+ " Attempting uninstall: transformers\n",
+ " Found existing installation: transformers 4.44.2\n",
+ " Uninstalling transformers-4.44.2:\n",
+ " Successfully uninstalled transformers-4.44.2\n",
+ "Successfully installed tokenizers-0.20.1 transformers-4.46.0.dev0\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!nvidia-smi"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "ofr1Btma0j05",
+ "outputId": "d775574e-65c2-417f-c450-16c7e32127e2"
+ },
+ "execution_count": 4,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Wed Oct 23 19:35:38 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 60C P8 11W / 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": "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": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 365,
+ "referenced_widgets": [
+ "d813349259244b4bb59301460ed6330c",
+ "b12a0ce4241e4d0487b846bb8a863105",
+ "9c1737b07ea648b99970f80050004943",
+ "c1e6d9e9cc89420e9721e12c44416b20",
+ "a57bba5b47774b769b1862e086fd9063",
+ "547bd8199a4345af9db78f2c641e630a",
+ "de667e70e7ac4eff8bf943c6b23fe3dd",
+ "ed1470bb918c4e0abe0edad0b5b6fd45",
+ "9fc7d3610be54f47a2f24321c8c96896",
+ "f61bc6fc98bd4598a91d7edf264311ff",
+ "9cfc593717f24b199c7b0de3c975ab94",
+ "fc4896248aa04218b62008da306a6ea4",
+ "6749ee35dcfc4d52a47b91e2180d4e9f",
+ "7d90e23719ed4899855fe5de542dc00a",
+ "1dc8a26de0fc4b6b9cfbb49a96f570f9",
+ "460246a51e994a5cb1fef011969e3abc",
+ "024132df9a694e58bee46fa7bb6402bc",
+ "60329e4b43cd42a1b3e3d4ed83a34b14",
+ "8597506d4aa242a6bc67116b961caa28",
+ "cbdd52f0a21548de895c4bdddee8e471",
+ "3bc5456f2d5347b8a52dc0323fafb701",
+ "75b8788cb1044f7fabdbd895e0c4178c",
+ "62090025878e4c0b97650ed20bb407b3",
+ "0700d0bd23fd47609964bab237df3b4c",
+ "e4c91f2bbb3345d095640d8fd40038d8",
+ "2f879970ce6a4f3db97eba191a02377e",
+ "12f8292acf2741d6bab9f646c71abf57",
+ "902ad28296824be29f67da3a1cdcffe9",
+ "8a85f3fda0794eab99e90f25319370a7",
+ "c3cb3e54e2574dada03443859ef1d677",
+ "1f8474762c404ebbb18900013ee274d5",
+ "01496832257b4bbfa26b353d81b0bd91",
+ "2912ce2b06574b1583998c36dbfb59fe",
+ "b0902d6015eb4828968eda920dd91f3e",
+ "a76766685d35445fb1bae9f4534eba4a",
+ "fdbc70b126fd41f1a7e67e51064dd716",
+ "3624a0daacce48679285c0d8197e5a69",
+ "e9d5743d1f51497c8cbd829b3ca0ab74",
+ "db2e0d3e4394461396c12fa94178ec51",
+ "6cff18a40352496c99d264197b8882e8",
+ "974c9e6551ef47cc95c116ab28d3daaa",
+ "0d075e33fe5c4ff48619749cf921e088",
+ "d0faff078ca647b4b25e6ba52ac61b1f",
+ "9ec6545a6e53407bb3c211c03d1bb56a",
+ "ab0c4107341346a1a86925a3bed6fdd3",
+ "bdf838289bc04dbea4a3a886bf89b2d8",
+ "ce8a25e22e764931b91c6f9706f065c3",
+ "b64d56b8d2fd4b34b2a9fd90d352ccae",
+ "53cc15c7f05849cc95cbef469024e64b",
+ "6500421e6caf40fbabc6b0badf4515d0",
+ "ec34b103c1f34339b2ddd1fbef4e5143",
+ "7ec72d7ea3364e5f834bdf0037ad65b1",
+ "f2abf754948e4d9aa91482d56d47644e",
+ "d791999926e44b788efaff0dc7c2cdce",
+ "3d3eaf9b74b04b4696d47ebca190046e",
+ "7556d07bb21444bfaa8f2cdfb4cfe9f6",
+ "881ef0f215054f7f88372420b5d0f4ad",
+ "3ac8fb59e54c46d3ae33ad60fb68f9fd",
+ "abc015efee3f44e8a87a4f84671b94a6",
+ "d80142607497456980a17a4d5f643868",
+ "9cf63afd44bd436b9bb9c1ccae9c8c07",
+ "78012e497b664e789b4d598643b36671",
+ "94c2df891fbf49528ee3f8b893189845",
+ "d26d0fb2f3f04518b1a59b72e3f5fafb",
+ "32c491e8ac204aad9529498810890076",
+ "9c5d3bdbb5384c18ad7cbd3a441eab4f",
+ "ec363c88a15047ddbdf5631ca8266ebf",
+ "9ea7007c27044f569f83ac743eeff18f",
+ "8d3c820f0191465298de0ffda370ebee",
+ "16ee2a0afe94476cbd8ad4f15da649e7",
+ "49e4c058527645faaaa77a59620673e5",
+ "5fcca0431a604c1b9502f6e345efe321",
+ "176f1faf080d4b719aa66ccc106bc3e8",
+ "1f3666b615d648c1b4993203dab1b2e7",
+ "c2a15fe11ed0407f9670a081e0dad4a3",
+ "89c6633e312b42f4831d5aa644355ea1",
+ "2e9ba156b2524cdab9a820c81ae11195"
+ ]
+ },
+ "id": "kd7cGSRA0mgT",
+ "outputId": "5cedaf85-c0df-4eef-9a40-c29dd9b196d8"
+ },
+ "execution_count": 5,
+ "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"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "preprocessor_config.json: 0%| | 0.00/433 [00:00 Dict[str, torch.Tensor]:\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, labels=label_features, 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",
+ " # 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",
+ " [\n",
+ " length - length % model.config.reduction_factor\n",
+ " for length in target_lengths\n",
+ " ]\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": "61i-jQMD6MdB"
+ },
+ "execution_count": 28,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "data_collator = TTSDataCollatorWithPadding(processor=processor)"
+ ],
+ "metadata": {
+ "id": "uqc9kx8o6Wml"
+ },
+ "execution_count": 29,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from transformers import SpeechT5ForTextToSpeech\n",
+ "\n",
+ "model = SpeechT5ForTextToSpeech.from_pretrained(checkpoint)"
+ ],
+ "metadata": {
+ "id": "fHqEPGhQ6aN-"
+ },
+ "execution_count": 30,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from functools import partial\n",
+ "\n",
+ "# disable cache during training since it's incompatible with gradient checkpointing\n",
+ "model.config.use_cache = False\n",
+ "\n",
+ "# set language and task for generation and re-enable cache\n",
+ "model.generate = partial(model.generate, use_cache=True)"
+ ],
+ "metadata": {
+ "id": "PLAQzsNU6fWY"
+ },
+ "execution_count": 31,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from transformers import Seq2SeqTrainingArguments\n",
+ "\n",
+ "training_args = Seq2SeqTrainingArguments(\n",
+ " output_dir=\"Bengali_finetuned_speecht5_tts\", # change to a repo name of your choice\n",
+ " per_device_train_batch_size=4,\n",
+ " gradient_accumulation_steps=8,\n",
+ " learning_rate=1e-4,\n",
+ " warmup_steps=100,\n",
+ " max_steps=600,\n",
+ " gradient_checkpointing=True,\n",
+ " fp16=True,\n",
+ " evaluation_strategy=\"steps\",\n",
+ " per_device_eval_batch_size=2,\n",
+ " save_steps=100,\n",
+ " eval_steps=100,\n",
+ " logging_steps=25,\n",
+ " report_to=[\"tensorboard\"],\n",
+ " load_best_model_at_end=True,\n",
+ " greater_is_better=False,\n",
+ " label_names=[\"labels\"],\n",
+ " push_to_hub=True,\n",
+ ")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "S0VFE6bq6jwp",
+ "outputId": "f7258053-b119-48d7-8ca7-68d0d4b184a3"
+ },
+ "execution_count": 32,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1559: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead\n",
+ " warnings.warn(\n"
+ ]
+ }
+ ]
+ },
+ {
+ "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": [
+ "713f8e05372e47be85a59444a1b0b510",
+ "03ee10a8b0644001b71d3c954cd26360",
+ "ca61abf022e74ae7afbc3dcf90c48da2",
+ "9364cc0b5f054ff7b45adcac46e5abdc",
+ "e1c441855894456ba6718458508800e8",
+ "0e22c1dfe50f438494052e2cae827652",
+ "8f370db9cdf647c5a036eb0a2807e748",
+ "df2cbd00a5be4d37a0c9767d7deca424",
+ "1b8c5540b96b4753b5ea19ad75c8adac",
+ "5ba2a255ed124a0a99007778481ed7f9",
+ "ca1a94565b4d447f815d7ed524dcc5c4",
+ "719028ff037b455cb61f7c253e80225a",
+ "ba346a9897c14aa2baf3122661e647c4",
+ "c76a965bc98846d8910c486fd5c921a6",
+ "7eddef91f2834556b3a97255b2d7fb26",
+ "d42baa2c44344d759961780cea35cf5c",
+ "5740988007d445ce95a50441e39edd0d",
+ "6bb1c267e50d4e3f9a91c28581a76ee6",
+ "fa0b7e1b4dcc42e6acb35c26d34204e3",
+ "256f373a047949238e1f535cb5c5a6e0",
+ "b03835162a27439cab59dbcda1b4d5f0",
+ "27e10a728fa24eccb924c51fe60ed742",
+ "09ee008fbafc47e59737187cc19063f1",
+ "a2d7942383984222ac4e2702ef5287b5",
+ "bffedc8730294232897b173ba25532c0",
+ "43dcfc7885ba4b40a97a57418370b402",
+ "e6e8fd4811294d358df763f3de509828",
+ "7391da7c12cb4c629b63a01ed3a9887b",
+ "72f276c1acbf4ebfab3fed66923883c0",
+ "cbec17a14fff4937aff83fd509e78bd2",
+ "f25a80bf8ef84b1fa152030fb785e430",
+ "ff460f1717744fa6838dd51d3fd1d40c"
+ ]
+ },
+ "id": "Lo3rCFsJ6zZG",
+ "outputId": "a5c0f775-7160-4d07-9df3-a234b32c7596"
+ },
+ "execution_count": 34,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "VBox(children=(HTML(value='| Step | \n", + "Training Loss | \n", + "Validation Loss | \n", + "
|---|---|---|
| 100 | \n", + "6.149900 | \n", + "0.708145 | \n", + "
| 200 | \n", + "5.451300 | \n", + "0.645911 | \n", + "
| 300 | \n", + "5.346100 | \n", + "0.641039 | \n", + "
| 400 | \n", + "5.129200 | \n", + "0.620839 | \n", + "
| 500 | \n", + "4.971700 | \n", + "0.619519 | \n", + "
| 600 | \n", + "4.916400 | \n", + "0.611307 | \n", + "
" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py:2816: UserWarning: Moving the following attributes in the config to the generation config: {'max_length': 1876}. You are seeing this warning because you've set generation parameters in the model config, as opposed to in the generation config.\n", + " warnings.warn(\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "TrainOutput(global_step=600, training_loss=5.65833683013916, metrics={'train_runtime': 1146.245, 'train_samples_per_second': 16.75, 'train_steps_per_second': 0.523, 'total_flos': 1044024322429440.0, 'train_loss': 5.65833683013916, 'epoch': 10.477223427331888})" + ] + }, + "metadata": {}, + "execution_count": 36 + } + ] + }, + { + "cell_type": "code", + "source": [ + "trainer.push_to_hub()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 52 + }, + "id": "wd6JbXmP6rzs", + "outputId": "af07674b-01ca-4239-cc93-a0a132fc4a51" + }, + "execution_count": 37, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "CommitInfo(commit_url='https://huggingface.co/DeepDiveDev/Bengali_finetuned_speecht5_tts/commit/0982ff27e1b848d2a3136c52c8f9c9cd96813d7a', commit_message='End of training', commit_description='', oid='0982ff27e1b848d2a3136c52c8f9c9cd96813d7a', pr_url=None, pr_revision=None, pr_num=None)" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 37 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "#Inference" + ], + "metadata": { + "id": "SZhUWEDS7fcj" + } + }, + { + "cell_type": "code", + "source": [ + "model = SpeechT5ForTextToSpeech.from_pretrained(\n", + " \"DeepDiveDev/Bengali_finetuned_speecht5_tts\"\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 113, + "referenced_widgets": [ + "38e3e52937544e618d771677eecb3bff", + "5fdeb6a293ce48668314f5a4cf0d687b", + "3fdf107667a541b0945637ee1add7bc4", + "b4d0abe867e440a49b97792fd92ff24f", + "24808ecbfbce400c927ff97fc105d988", + "80539e6a410c4c3a899deb5156e7fd60", + "989665d0e97f4b809f2e132a79db276e", + "f48db0eacde64f1f8f29329dcacd0e72", + "facca2a4a5b1461ca070b42f4cb1c892", + "c64e4b85bc17470ba2281f78ed2dd071", + "adbbbc6c122248f3ad825362518e9b00", + "c98600cd1fb747d983e596c539b2ffc6", + "fe1653f3ced04930b8678e3260916925", + "d22ae661dc884b2087b0fe70ceac9f8c", + "b2a10fcabd0b4978aad299ee4e69f661", + "e73ba61368794fec991c62e4985984b1", + "91bb4537e7b344d5b7e4c317a885f078", + "818bf1fdad494649b255b159ba05e720", + "5d356bb6d9024d2a9cc2e604e833d6e3", + "b14b38ca7ec44feca308fd07226a0feb", + "5cdf3401323841e7b2da86fdd941febc", + "0e3e6d6ea4164708a913356264bb8ce0", + "db230af9f78a43d9bc98f376cc442577", + "b7fc6bd8a8f148fea2d6fe197ca21162", + "20e21028fbbf47a8be2352da4a47d07c", + "12a3e0832238417dbc1731c4c13da818", + "def6aa3570f94a3da19d6de45ecf7cb5", + "947b4163505d4fcebb7757ed7ff71400", + "642b10531a1142d88d1aaebe55864f9b", + "62962d210bcd4cd0b84ab02f153cb297", + "bb5a2fef47834688b0c058872ea728bc", + "d64085f5c9334c9492b67861fde987cb", + "f5d47bb728594b70a8f31adfe05b21dc" + ] + }, + "id": "v6PbDn6C7nZB", + "outputId": "a3de436a-154c-4c98-a37f-bb84785c4755" + }, + "execution_count": 38, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "config.json: 0%| | 0.00/2.11k [00:00 1 else \"শত\") + (\" \" + number_to_words(remainder) if remainder else \"\")\n", + " elif number < 1000000:\n", + " thousands, remainder = divmod(number, 1000)\n", + " return (number_to_words(thousands) + \" হাজার\" if thousands > 1 else \"হাজার\") + (\" \" + number_to_words(remainder) if remainder else \"\")\n", + " elif number < 1000000000:\n", + " millions, remainder = divmod(number, 1000000)\n", + " return number_to_words(millions) + \" মিলিয়ন\" + (\" \" + number_to_words(remainder) if remainder else \"\")\n", + " elif number < 1000000000000:\n", + " billions, remainder = divmod(number, 1000000000)\n", + " return number_to_words(billions) + \" বিলিয়ন\" + (\" \" + number_to_words(remainder) if remainder else \"\")\n", + " else:\n", + " return str(number)\n", + "\n", + "def replace_numbers_with_words(text):\n", + "\n", + " def replace(match):\n", + " number = int(match.group())\n", + " return number_to_words(number)\n", + "\n", + " # Find the numbers and replace with words\n", + " result = re.sub(r'\\b\\d+\\b', replace, text)\n", + "\n", + " return result" + ], + "metadata": { + "id": "bykKmv6m8BTL" + }, + "execution_count": 42, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "# Function to clean up text using the replacement pairs\n", + "def cleanup_text(text):\n", + " for src, dst in replacements:\n", + " text = text.replace(src, dst)\n", + " return text" + ], + "metadata": { + "id": "GePrmEvz8bR1" + }, + "execution_count": 43, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "converted_text = replace_numbers_with_words(text)\n", + "cleaned_text = cleanup_text(converted_text)\n", + "final_text = normalize_text(cleaned_text)\n", + "final_text" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 36 + }, + "id": "q6cv22Ve8hTV", + "outputId": "6e866ed8-a209-441f-eb12-e0940df4681f" + }, + "execution_count": 44, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "'aam mshn lrn ny kj krchh'" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 44 + } + ] + }, + { + "cell_type": "code", + "source": [ + "inputs = processor(text=final_text, return_tensors=\"pt\")" + ], + "metadata": { + "id": "vuIpzB5e8kG8" + }, + "execution_count": 45, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "from transformers import SpeechT5HifiGan\n", + "\n", + "vocoder = SpeechT5HifiGan.from_pretrained(\"microsoft/speecht5_hifigan\")\n", + "speech = model.generate_speech(inputs[\"input_ids\"], speaker_embeddings, vocoder=vocoder)" + ], + "metadata": { + "id": "Zuwlqj1R8oOi" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "from transformers import SpeechT5HifiGan, SpeechT5ForTextToSpeech, SpeechT5Tokenizer\n", + "from speechbrain.pretrained import EncoderClassifier\n", + "import torch\n", + "import soundfile as sf\n", + "from IPython.display import Audio\n", + "\n", + "# Load the model, tokenizer, and vocoder\n", + "model_id = \"microsoft/speecht5_tts\"\n", + "model = SpeechT5ForTextToSpeech.from_pretrained(model_id)\n", + "tokenizer = SpeechT5Tokenizer.from_pretrained(model_id)\n", + "vocoder = SpeechT5HifiGan.from_pretrained(\"microsoft/speecht5_hifigan\")\n", + "\n", + "# Load pre-trained speaker embeddings using SpeechBrain (speechbrain/spkrec-xvect-voxceleb)\n", + "classifier = EncoderClassifier.from_hparams(source=\"speechbrain/spkrec-xvect-voxceleb\")\n", + "\n", + "# Generate a dummy audio input for speaker embedding (since speaker embeddings are usually from audio)\n", + "# Replace 'your_audio_file.wav' with the actual path of an audio file if you have one.\n", + "signal, fs = torch.randn(1, 16000), 16000 # Example dummy audio, replace this with real audio\n", + "\n", + "# Extract speaker embeddings\n", + "speaker_embeddings = classifier.encode_batch(signal)\n", + "\n", + "# Prepare your input text\n", + "text = \"This is a test.\"\n", + "inputs = tokenizer(text, return_tensors=\"pt\")\n", + "\n", + "# Generate speech\n", + "try:\n", + " speech = model.generate_speech(inputs[\"input_ids\"], speaker_embeddings, vocoder=vocoder)\n", + "\n", + " # Play the audio\n", + " display(Audio(speech.numpy(), rate=16000))\n", + "\n", + " # Save the audio to a file (e.g., 'output.wav')\n", + " sf.write('output.wav', speech.numpy(), 16000)\n", + "\n", + "except Exception as e:\n", + " print(f\"Error generating speech: {e}\")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "zdEKGZSABuCI", + "outputId": "18463053-8992-4065-fd0a-b5967b6a98da" + }, + "execution_count": 53, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.10/dist-packages/speechbrain/utils/checkpoints.py:147: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n", + " torch.load(path, map_location=device), strict=False\n", + "/usr/local/lib/python3.10/dist-packages/speechbrain/processing/features.py:1215: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n", + " stats = torch.load(path, map_location=device)\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Error generating speech: expand(torch.FloatTensor{[1, 1, 1, 512]}, size=[-1, 1, -1]): the number of sizes provided (3) must be greater or equal to the number of dimensions in the tensor (4)\n" + ] + } + ] + } + ] +} \ No newline at end of file