{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "4d50310e-f094-42e0-af30-1e42b13ceb95",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2023-04-22 16:58:42.388656: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"2023-04-22 16:58:43.345225: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
]
}
],
"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": 2,
"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": 3,
"id": "9413f553-5bd0-4820-bad4-edd7fd7d2370",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[0m\u001b[01;34mangie\u001b[0m/ \u001b[01;34mfreeman\u001b[0m/ \u001b[01;34mmyself\u001b[0m/ \u001b[01;34mtom\u001b[0m/ \u001b[01;34mtrain_grace\u001b[0m/\n",
"\u001b[01;34mapplejack\u001b[0m/ \u001b[01;34mgeralt\u001b[0m/ \u001b[01;34mpat\u001b[0m/ \u001b[01;34mtrain_atkins\u001b[0m/ \u001b[01;34mtrain_kennard\u001b[0m/\n",
"\u001b[01;34mcond_latent_example\u001b[0m/ \u001b[01;34mhalle\u001b[0m/ \u001b[01;34mpat2\u001b[0m/ \u001b[01;34mtrain_daws\u001b[0m/ \u001b[01;34mtrain_lescault\u001b[0m/\n",
"\u001b[01;34mdaniel\u001b[0m/ \u001b[01;34mjlaw\u001b[0m/ \u001b[01;34mrainbow\u001b[0m/ \u001b[01;34mtrain_dotrice\u001b[0m/ \u001b[01;34mtrain_mouse\u001b[0m/\n",
"\u001b[01;34mdeniro\u001b[0m/ \u001b[01;34mlj\u001b[0m/ \u001b[01;34msnakes\u001b[0m/ \u001b[01;34mtrain_dreams\u001b[0m/ \u001b[01;34mweaver\u001b[0m/\n",
"\u001b[01;34memma\u001b[0m/ \u001b[01;34mmol\u001b[0m/ \u001b[01;34mtim_reynolds\u001b[0m/ \u001b[01;34mtrain_empire\u001b[0m/ \u001b[01;34mwilliam\u001b[0m/\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%ls ../TTS/tts/utils/assets/tortoise/voices/\n",
"import IPython\n",
"IPython.display.Audio(filename='../TTS/tts/utils/assets/tortoise/voices/tom/1.wav')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "96a98ae5-313b-40d1-9311-5a785f2c9a4e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"mode 0\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/manmay/anaconda3/envs/tts/lib/python3.8/site-packages/torch/functional.py:641: UserWarning: stft with return_complex=False is deprecated. In a future pytorch release, stft will return complex tensors for all inputs, and return_complex=False will raise an error.\n",
"Note: you can still call torch.view_as_real on the complex output to recover the old return format. (Triggered internally at /opt/conda/conda-bld/pytorch_1678402379298/work/aten/src/ATen/native/SpectralOps.cpp:862.)\n",
" return _VF.stft(input, n_fft, hop_length, win_length, window, # type: ignore[attr-defined]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Generating autoregressive samples..\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 16/16 [01:05<00:00, 4.11s/it]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Computing best candidates using CLVP\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 16/16 [00:05<00:00, 3.14it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Transforming autoregressive outputs into audio..\n"
]
},
{
"data": {
"application/json": {
"ascii": false,
"bar_format": null,
"colour": null,
"elapsed": 0.06691813468933105,
"initial": 0,
"n": 0,
"ncols": null,
"nrows": 25,
"postfix": null,
"prefix": "",
"rate": null,
"total": 50,
"unit": "it",
"unit_divisor": 1000,
"unit_scale": false
},
"application/vnd.jupyter.widget-view+json": {
"model_id": "19f00339415746cbbfdf4cf70c84b88a",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/50 [00:00\n",
" \n",
" Your browser does not support the audio element.\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#@markdown Pick one of the voices from the output above\n",
"voice = 'tom' #@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
}