Colab notebook (part 1)

main.py

@@ -0,0 +1,27 @@
+import webui as mrq
+
+if __name__ == "__main__":
+    mrq.args = mrq.setup_args()
+
+    if mrq.args.listen_path is not None and mrq.args.listen_path != "/":
+        import uvicorn
+        uvicorn.run("main:app", host=mrq.args.listen_host, port=mrq.args.listen_port if not None else 8000)
+    else:
+        mrq.webui = mrq.setup_gradio()
+        mrq.webui.launch(share=mrq.args.share, prevent_thread_lock=True, server_name=mrq.args.listen_host, server_port=mrq.args.listen_port)
+        mrq.tts = mrq.setup_tortoise()
+
+        mrq.webui.block_thread()
+elif __name__ == "main":
+    from fastapi import FastAPI
+    import gradio as gr
+
+    import sys
+    sys.argv = [sys.argv[0]]
+
+    app = FastAPI()
+    mrq.args = mrq.setup_args()
+    mrq.webui = mrq.setup_gradio()
+    app = gr.mount_gradio_app(app, mrq.webui, path=mrq.args.listen_path)
+
+    mrq.tts = mrq.setup_tortoise()

start.bat

@@ -1,4 +1,4 @@
 call .\tortoise-venv\Scripts\activate.bat
-python app.py
+python main.py
 deactivate
 pause

start.sh

@@ -1,3 +1,3 @@
 source ./tortoise-venv/bin/activate
-python ./app.py
+python3 ./main.py
 deactivate

tortoise_tts.ipynb

@@ -1,185 +1 @@
-{
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "name": "tortoise-tts.ipynb",
-      "provenance": [],
-      "collapsed_sections": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    },
-    "accelerator": "GPU"
-  },
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "source": [
-        "Welcome to Tortoise! 🐢🐢🐢🐢\n",
-        "\n",
-        "Before you begin, I **strongly** recommend you turn on a GPU runtime.\n",
-        "\n",
-        "There's a reason this is called \"Tortoise\" - this model takes up to a minute to perform inference for a single sentence on a GPU. Expect waits on the order of hours on a CPU."
-      ],
-      "metadata": {
-        "id": "_pIZ3ZXNp7cf"
-      }
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "JrK20I32grP6"
-      },
-      "outputs": [],
-      "source": [
-        "!git clone https://github.com/neonbjb/tortoise-tts.git\n",
-        "%cd tortoise-tts\n",
-        "!pip3 install -r requirements.txt\n",
-        "!python3 setup.py install"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Imports used through the rest of the notebook.\n",
-        "import torch\n",
-        "import torchaudio\n",
-        "import torch.nn as nn\n",
-        "import torch.nn.functional as F\n",
-        "\n",
-        "import IPython\n",
-        "\n",
-        "from tortoise.api import TextToSpeech\n",
-        "from tortoise.utils.audio import load_audio, load_voice, load_voices\n",
-        "\n",
-        "# This will download all the models used by Tortoise from the HF hub.\n",
-        "tts = TextToSpeech()"
-      ],
-      "metadata": {
-        "id": "Gen09NM4hONQ"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# This is the text that will be spoken.\n",
-        "text = \"Joining two modalities results in a surprising increase in generalization! What would happen if we combined them all?\"\n",
-        "\n",
-        "# Here's something for the poetically inclined.. (set text=)\n",
-        "\"\"\"\n",
-        "Then took the other, as just as fair,\n",
-        "And having perhaps the better claim,\n",
-        "Because it was grassy and wanted wear;\n",
-        "Though as for that the passing there\n",
-        "Had worn them really about the same,\"\"\"\n",
-        "\n",
-        "# Pick a \"preset mode\" to determine quality. Options: {\"ultra_fast\", \"fast\" (default), \"standard\", \"high_quality\"}. See docs in api.py\n",
-        "preset = \"fast\""
-      ],
-      "metadata": {
-        "id": "bt_aoxONjfL2"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Tortoise will attempt to mimic voices you provide. It comes pre-packaged\n",
-        "# with some voices you might recognize.\n",
-        "\n",
-        "# Let's list all the voices available. These are just some random clips I've gathered\n",
-        "# from the internet as well as a few voices from the training dataset.\n",
-        "# Feel free to add your own clips to the voices/ folder.\n",
-        "%ls tortoise/voices\n",
-        "\n",
-        "IPython.display.Audio('tortoise/voices/tom/1.wav')"
-      ],
-      "metadata": {
-        "id": "SSleVnRAiEE2"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Pick one of the voices from the output above\n",
-        "voice = 'tom'\n",
-        "\n",
-        "# Load it and send it through Tortoise.\n",
-        "voice_samples, conditioning_latents = load_voice(voice)\n",
-        "gen = tts.tts_with_preset(text, voice_samples=voice_samples, conditioning_latents=conditioning_latents, \n",
-        "                          preset=preset)\n",
-        "torchaudio.save('generated.wav', gen.squeeze(0).cpu(), 24000)\n",
-        "IPython.display.Audio('generated.wav')"
-      ],
-      "metadata": {
-        "id": "KEXOKjIvn6NW"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Tortoise can also generate speech using a random voice. The voice changes each time you execute this!\n",
-        "# (Note: random voices can be prone to strange utterances)\n",
-        "gen = tts.tts_with_preset(text, voice_samples=None, conditioning_latents=None, preset=preset)\n",
-        "torchaudio.save('generated.wav', gen.squeeze(0).cpu(), 24000)\n",
-        "IPython.display.Audio('generated.wav')"
-      ],
-      "metadata": {
-        "id": "16Xs2SSC3BXa"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# You can also combine conditioning voices. Combining voices produces a new voice\n",
-        "# with traits from all the parents.\n",
-        "#\n",
-        "# Lets see what it would sound like if Picard and Kirk had a kid with a penchant for philosophy:\n",
-        "voice_samples, conditioning_latents = load_voices(['pat', 'william'])\n",
-        "\n",
-        "gen = tts.tts_with_preset(\"They used to say that if man was meant to fly, he’d have wings. But he did fly. He discovered he had to.\", \n",
-        "                          voice_samples=None, conditioning_latents=None, preset=preset)\n",
-        "torchaudio.save('captain_kirkard.wav', gen.squeeze(0).cpu(), 24000)\n",
-        "IPython.display.Audio('captain_kirkard.wav')"
-      ],
-      "metadata": {
-        "id": "fYTk8KUezUr5"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "del tts  # Will break other cells, but necessary to conserve RAM if you want to run this cell.\n",
-        "\n",
-        "# Tortoise comes with some scripts that does a lot of the lifting for you. For example,\n",
-        "# read.py will read a text file for you.\n",
-        "!python3 tortoise/read.py --voice=train_atkins --textfile=tortoise/data/riding_hood.txt --preset=ultra_fast --output_path=.\n",
-        "\n",
-        "IPython.display.Audio('train_atkins/combined.wav')\n",
-        "# This will take awhile.."
-      ],
-      "metadata": {
-        "id": "t66yqWgu68KL"
-      },
-      "execution_count": null,
-      "outputs": []
-    }
-  ]
-}
+{"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/tortoise-tts/\n","%cd tortoise-tts\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\n","!pip install Pillow==9.0.0 # errors out only when importing\n","!python setup.py install"]},{"cell_type":"markdown","source":["## Running"],"metadata":{"id":"o1gkfw3B3JSk"}},{"cell_type":"code","source":["import webui as mrq\n","\n","mrq.args = mrq.setup_args()\n","mrq.webui = mrq.setup_gradio()\n","mrq.webui.launch(share=True, prevent_thread_lock=True)\n","mrq.tts = mrq.setup_tortoise()\n","mrq.webui.block_thread()"],"metadata":{"id":"c_EQZLTA19c7"},"execution_count":null,"outputs":[]}]}

webui.py

@@ -20,6 +20,10 @@ from tortoise.api import TextToSpeech
 from tortoise.utils.audio import load_audio, load_voice, load_voices
 from tortoise.utils.text import split_and_recombine_text
 
+args = None
+webui = None
+tts = None
+
 def generate(text, delimiter, emotion, prompt, voice, mic_audio, seed, candidates, num_autoregressive_samples, diffusion_iterations, temperature, diffusion_sampler, breathing_room, cvvp_weight, experimentals, progress=gr.Progress(track_tqdm=True)):
     try:
         tts
@@ -424,7 +428,7 @@ def setup_args():
     args.listen_host = None
     args.listen_port = None
     args.listen_path = None
-    if args.listen is not None:
+    if args.listen:
         match = re.findall(r"^(?:(.+?):(\d+))?(\/.+?)?$", args.listen)[0]
 
         args.listen_host = match[0] if match[0] != "" else "127.0.0.1"
@@ -623,29 +627,4 @@ def setup_gradio():
 
     webui.queue(concurrency_count=args.concurrency_count)
 
-    return webui
-
-if __name__ == "__main__":
-    args = setup_args()
-
-    if args.listen_path is not None and args.listen_path != "/":
-        import uvicorn
-        uvicorn.run("app:app", host=args.listen_host, port=args.listen_port if not None else 8000)
-    else:
-        webui = setup_gradio()
-        webui.launch(share=args.share, prevent_thread_lock=True, server_name=args.listen_host, server_port=args.listen_port)
-        tts = setup_tortoise()
-
-        webui.block_thread()
-elif __name__ == "app":
-    import sys
-    from fastapi import FastAPI
-
-    sys.argv = [sys.argv[0]]
-
-    app = FastAPI()
-    args = setup_args()
-    webui = setup_gradio()
-    app = gr.mount_gradio_app(app, webui, path=args.listen_path)
-
-    tts = setup_tortoise()
+    return webui