File size: 3,446 Bytes
8520a55 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install --upgrade vocos encodec librosa"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"import pprint\n",
"import IPython.display as ipd\n",
"import torch\n",
"import librosa"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load model\n",
"mars5, config_class = torch.hub.load('Camb-ai/mars5-tts', 'mars5_english', trust_repo=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now that the model is loaded, pick a reference audio to clone from. If you want to use deep clone, also specify its transcript. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# download example ref audio\n",
"!wget -O example.wav https://github.com/Camb-ai/mars5-tts/raw/master/docs/assets/example_ref.wav "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"wav, sr = librosa.load('./example.wav', \n",
" sr=mars5.sr, mono=True)\n",
"wav = torch.from_numpy(wav)\n",
"ref_transcript = \"We actually haven't managed to meet demand.\"\n",
"print(\"Reference audio:\")\n",
"ipd.display(ipd.Audio(wav.numpy(), rate=mars5.sr))\n",
"print(f\"Reference transcript: {ref_transcript}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"deep_clone = True # set to False if you don't know prompt transcript or want fast inference.\n",
"# Below you can tune other inference settings, like top_k, temperature, top_p, etc...\n",
"cfg = config_class(deep_clone=deep_clone, rep_penalty_window=100,\n",
" top_k=100, temperature=0.7, freq_penalty=3)\n",
"\n",
"ar_codes, wav_out = mars5.tts(\"The quick brown rat.\", wav, \n",
" ref_transcript,\n",
" cfg=cfg)\n",
"\n",
"print('Synthesized output audio:')\n",
"ipd.Audio(wav_out.numpy(), rate=mars5.sr)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can see all the inference settings available to tune in the inference config here:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pprint.pprint(config_class())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can also listen to the vocoded raw coarse codes, for debugging purposes:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ar_wav = mars5.vocode(ar_codes.cpu()[:, None])\n",
"ipd.Audio(ar_wav.numpy(), rate=mars5.sr)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "matt-py311",
"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": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|