tortoise-tts/tortoise_tts.ipynb

{
   "nbformat":4,
   "nbformat_minor":0,
   "metadata":{
      "colab":{
         "private_outputs":true,
         "provenance":[
            
         ]
      },
      "kernelspec":{
         "name":"python3",
         "display_name":"Python 3"
      },
      "language_info":{
         "name":"python"
      },
      "accelerator":"GPU",
      "gpuClass":"standard"
   },
   "cells":[
      {
         "cell_type":"markdown",
         "source":[
            "## Initialization"
         ],
         "metadata":{
            "id":"ni41hmE03DL6"
         }
      },
      {
         "cell_type":"code",
         "execution_count":null,
         "metadata":{
            "id":"FtsMKKfH18iM"
         },
         "outputs":[
            
         ],
         "source":[
            "!git clone https://git.ecker.tech/mrq/ai-voice-cloning/\n",
            "%cd ai-voice-cloning\n",
            "!python -m pip install --upgrade pip\n",
            "!pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116\n",
            "!python -m pip install -r ./requirements.txt"
         ]
      },
      {
         "cell_type":"code",
         "source":[
            "# colab requires the runtime to restart before use\n",
            "exit()"
         ],
         "metadata":{
            "id":"FVUOtSASCSJ8"
         },
         "execution_count":null,
         "outputs":[
            
         ]
      },
      {
         "cell_type":"markdown",
         "source":[
            "## Running"
         ],
         "metadata":{
            "id":"o1gkfw3B3JSk"
         }
      },
      {
         "cell_type":"code",
         "source":[
            "%cd /content/ai-voice-cloning\n",
            "\n",
            "import os\n",
            "import sys\n",
            "\n",
            "sys.argv = [\"\"]\n",
            "sys.path.append('./src/')\n",
            "\n",
            "if 'TORTOISE_MODELS_DIR' not in os.environ:\n",
            "\tos.environ['TORTOISE_MODELS_DIR'] = os.path.realpath(os.path.join(os.getcwd(), './models/tortoise/'))\n",
            "\n",
            "if 'TRANSFORMERS_CACHE' not in os.environ:\n",
            "\tos.environ['TRANSFORMERS_CACHE'] = os.path.realpath(os.path.join(os.getcwd(), './models/transformers/'))\n",
            "\n",
            "from utils import *\n",
            "from webui import *\n",
            "\n",
            "args = setup_args()\n",
            "\n",
            "webui = setup_gradio()\n",
            "tts = setup_tortoise()\n",
            "webui.launch(share=True, prevent_thread_lock=True, height=1000)\n",
            "webui.block_thread()"
         ],
         "metadata":{
            "id":"c_EQZLTA19c7"
         },
         "execution_count":null,
         "outputs":[
            
         ]
      },
      {
         "cell_type":"markdown",
         "source":[
            "## Exporting"
         ],
         "metadata":{
            "id":"2AnVQxEJx47p"
         }
      },
      {
         "cell_type":"code",
         "source":[
            "%cd /content/ai-voice-cloning\n",
            "!apt install -y p7zip-full\n",
            "from datetime import datetime\n",
            "timestamp = datetime.now().strftime('%m-%d-%Y_%H:%M:%S')\n",
            "!mkdir -p \"../{timestamp}\"\n",
            "!mv ./results/* \"../{timestamp}/.\"\n",
            "!7z a -t7z -m0=lzma2 -mx=9 -mfb=64 -md=32m -ms=on \"../{timestamp}.7z\" \"../{timestamp}/\"\n",
            "!ls ~/\n",
            "!echo \"Finished zipping, archive is available at {timestamp}.7z\""
         ],
         "metadata":{
            "id":"YOACiDCXx72G"
         },
         "execution_count":null,
         "outputs":[
            
         ]
      }
   ]
}