File size: 3,905 Bytes
91670c0 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 |
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Install Dependencies"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# !pip install -q torchaudio\n",
"SAMPLING_RATE = 16000\n",
"import torch\n",
"from pprint import pprint\n",
"\n",
"torch.set_num_threads(1)\n",
"NUM_PROCESS=4 # set to the number of CPU cores in the machine\n",
"NUM_COPIES=8\n",
"# download wav files, make multiple copies\n",
"for idx in range(NUM_COPIES):\n",
" torch.hub.download_url_to_file('https://models.silero.ai/vad_models/en.wav', f\"en_example{idx}.wav\")\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load VAD model from torch hub"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad',\n",
" model='silero_vad',\n",
" force_reload=True,\n",
" onnx=False)\n",
"\n",
"(get_speech_timestamps,\n",
"save_audio,\n",
"read_audio,\n",
"VADIterator,\n",
"collect_chunks) = utils"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define a vad process function"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import multiprocessing\n",
"\n",
"vad_models = dict()\n",
"\n",
"def init_model(model):\n",
" pid = multiprocessing.current_process().pid\n",
" model, _ = torch.hub.load(repo_or_dir='snakers4/silero-vad',\n",
" model='silero_vad',\n",
" force_reload=False,\n",
" onnx=False)\n",
" vad_models[pid] = model\n",
"\n",
"def vad_process(audio_file: str):\n",
" \n",
" pid = multiprocessing.current_process().pid\n",
" \n",
" with torch.no_grad():\n",
" wav = read_audio(audio_file, sampling_rate=SAMPLING_RATE)\n",
" return get_speech_timestamps(\n",
" wav,\n",
" vad_models[pid],\n",
" 0.46, # speech prob threshold\n",
" 16000, # sample rate\n",
" 300, # min speech duration in ms\n",
" 20, # max speech duration in seconds\n",
" 600, # min silence duration\n",
" 512, # window size\n",
" 200, # spech pad ms\n",
" )"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Parallelization"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from concurrent.futures import ProcessPoolExecutor, as_completed\n",
"\n",
"futures = []\n",
"\n",
"with ProcessPoolExecutor(max_workers=NUM_PROCESS, initializer=init_model, initargs=(model,)) as ex:\n",
" for i in range(NUM_COPIES):\n",
" futures.append(ex.submit(vad_process, f\"en_example{idx}.wav\"))\n",
"\n",
"for finished in as_completed(futures):\n",
" pprint(finished.result())"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "diarization",
"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": "3.9.15"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|