TTS/notebooks/Tortoise.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4d50310e-f094-42e0-af30-1e42b13ceb95",
   "metadata": {},
   "outputs": [],
   "source": [
    "#@title # Setup\n",
    "# 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 TTS.tts.models.tortoise import TextToSpeech\n",
    "from TTS.tts.layers.tortoise.audio_utils import load_audio, load_voice, load_voices\n",
    "\n",
    "# This will download all the models used by Tortoise from the HuggingFace hub.\n",
    "tts = TextToSpeech()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e126c3c3-d90a-492f-b5bb-0d86587f15cc",
   "metadata": {},
   "outputs": [],
   "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?\" #@param {type:\"string\"}\n",
    "#@markdown Show code for multiline text input\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\" #@param [\"ultra_fast\", \"fast\", \"standard\", \"high_quality\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9413f553-5bd0-4820-bad4-edd7fd7d2370",
   "metadata": {},
   "outputs": [],
   "source": [
    "%ls ../TTS/tts/utils/assets/tortoise/voices/\n",
    "import IPython\n",
    "IPython.display.Audio(filename='../TTS/tts/utils/assets/tortoise/voices/lj/1.wav')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "96a98ae5-313b-40d1-9311-5a785f2c9a4e",
   "metadata": {},
   "outputs": [],
   "source": [
    "#@markdown Pick one of the voices from the output above\n",
    "voice = 'lj' #@param {type:\"string\"}\n",
    "\n",
    "#@markdown 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')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "04e473e5-c489-4a78-aa11-03e89a778ed8",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}