Upload text2speech.ipynb

text2speech.ipynb

@@ -0,0 +1,96 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "fce4ae66-1841-45b4-a0c0-6202287437d4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/hubsnippet/.local/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n",
+      "None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan\n",
+    "#from datasets import load_dataset\n",
+    "#import torch\n",
+    "import soundfile as sf\n",
+    "#from datasets import load_dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2c4a3d90-f2ac-440a-a7ff-011fab098867",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ImportError",
+     "evalue": "\nSpeechT5Tokenizer requires the SentencePiece library but it was not found in your environment. Checkout the instructions on the\ninstallation page of its repo: https://github.com/google/sentencepiece#installation and follow the ones\nthat match your environment. Please note that you may need to restart your runtime after installation.\n",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mImportError\u001b[0m                               Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[2], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m processor \u001b[38;5;241m=\u001b[39m \u001b[43mSpeechT5Processor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmicrosoft/speecht5_tts\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      2\u001b[0m model \u001b[38;5;241m=\u001b[39m SpeechT5ForTextToSpeech\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmicrosoft/speecht5_tts\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      3\u001b[0m vocoder \u001b[38;5;241m=\u001b[39m SpeechT5HifiGan\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmicrosoft/speecht5_hifigan\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/transformers/processing_utils.py:465\u001b[0m, in \u001b[0;36mProcessorMixin.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, cache_dir, force_download, local_files_only, token, revision, **kwargs)\u001b[0m\n\u001b[1;32m    462\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m token \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    463\u001b[0m     kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtoken\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m token\n\u001b[0;32m--> 465\u001b[0m args \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_arguments_from_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    466\u001b[0m processor_dict, kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mget_processor_dict(pretrained_model_name_or_path, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    468\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mfrom_args_and_dict(args, processor_dict, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
+      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/transformers/processing_utils.py:511\u001b[0m, in \u001b[0;36mProcessorMixin._get_arguments_from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    508\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    509\u001b[0m         attribute_class \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(transformers_module, class_name)\n\u001b[0;32m--> 511\u001b[0m     args\u001b[38;5;241m.\u001b[39mappend(\u001b[43mattribute_class\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m(pretrained_model_name_or_path, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs))\n\u001b[1;32m    512\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m args\n",
+      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/transformers/utils/import_utils.py:1450\u001b[0m, in \u001b[0;36mDummyObject.__getattribute__\u001b[0;34m(cls, key)\u001b[0m\n\u001b[1;32m   1448\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m key\u001b[38;5;241m.\u001b[39mstartswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mand\u001b[39;00m key \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_from_config\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m   1449\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__getattribute__\u001b[39m(key)\n\u001b[0;32m-> 1450\u001b[0m \u001b[43mrequires_backends\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_backends\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/transformers/utils/import_utils.py:1438\u001b[0m, in \u001b[0;36mrequires_backends\u001b[0;34m(obj, backends)\u001b[0m\n\u001b[1;32m   1436\u001b[0m failed \u001b[38;5;241m=\u001b[39m [msg\u001b[38;5;241m.\u001b[39mformat(name) \u001b[38;5;28;01mfor\u001b[39;00m available, msg \u001b[38;5;129;01min\u001b[39;00m checks \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m available()]\n\u001b[1;32m   1437\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m failed:\n\u001b[0;32m-> 1438\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(failed))\n",
+      "\u001b[0;31mImportError\u001b[0m: \nSpeechT5Tokenizer requires the SentencePiece library but it was not found in your environment. Checkout the instructions on the\ninstallation page of its repo: https://github.com/google/sentencepiece#installation and follow the ones\nthat match your environment. Please note that you may need to restart your runtime after installation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "processor = SpeechT5Processor.from_pretrained(\"microsoft/speecht5_tts\")\n",
+    "model = SpeechT5ForTextToSpeech.from_pretrained(\"microsoft/speecht5_tts\")\n",
+    "vocoder = SpeechT5HifiGan.from_pretrained(\"microsoft/speecht5_hifigan\")\n",
+    "\n",
+    "inputs = processor(text=\"Hello, my dog is cute.\", return_tensors=\"pt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0fd02046-1a29-4989-9031-4b7d1729a336",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# load xvector containing speaker's voice characteristics from a dataset\n",
+    "#embeddings_dataset = load_dataset(\"Matthijs/cmu-arctic-xvectors\", split=\"validation\")\n",
+    "#speaker_embeddings = torch.tensor(embeddings_dataset[7306][\"xvector\"]).unsqueeze(0)\n",
+    "\n",
+    "speech = model.generate_speech(inputs[\"input_ids\"], vocoder=vocoder)\n",
+    "\n",
+    "sf.write(\"speech.wav\", speech.numpy(), samplerate=16000)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}