File size: 3,156 Bytes
93a0cf7 | 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 | {
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from audio_utils import audio_stream_generator\n",
"import IPython.display as ipd\n",
"import sys\n",
"sys.path.append(\"..\")\n",
"from transcribe.helpers.vadprocessor import FixedVADIterator\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"vac = FixedVADIterator(\n",
" threshold=0.5,\n",
" sampling_rate=16000,\n",
" # speech_pad_ms=10\n",
" min_silence_duration_ms = 100,\n",
" # speech_pad_ms = 30,\n",
" max_speech_duration_s=5.0,\n",
" )\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"SAMPLE_FILE_PATH = \"/Users/david/Samples/Audio/zh/liyongle.wav\"\n",
"SAMPLING_RATE = 16000\n",
"\n",
"chunks_generator = audio_stream_generator(SAMPLE_FILE_PATH, chunk_size=4096)\n",
"vac.reset_states()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"已加载音频文件: /Users/david/Samples/Audio/zh/liyongle.wav\n",
"采样率: 16000 Hz\n",
"音频长度: 64.00 秒\n",
"{'start': 3616}\n",
"{'end': 83968}\n",
"{'end': 164352}\n",
"{'end': 244736}\n",
"{'end': 325120}\n",
"{'end': 405504}\n",
"{'end': 485888}\n",
"{'end': 566272}\n",
"{'end': 624608}\n",
"{'start': 631328}\n",
"{'end': 691168}\n",
"{'start': 698912}\n",
"{'end': 779264}\n",
"{'end': 800736}\n",
"{'start': 805920}\n",
"{'end': 846816}\n",
"{'start': 855072}\n",
"{'end': 862176}\n",
"{'start': 864288}\n",
"{'end': 890336}\n",
"{'start': 893984}\n",
"{'end': 912352}\n",
"{'start': 917536}\n",
"{'end': 932320}\n",
"{'start': 939040}\n",
"{'end': 966112}\n",
"{'start': 970784}\n",
"{'end': 1015264}\n",
"{'start': 1019424}\n",
"音频流处理完成\n"
]
}
],
"source": [
"for chunk in chunks_generator:\n",
" # vad_iterator.reset_states()\n",
" # audio_buffer = np.append(audio_buffer, chunk)\n",
" \n",
" speech_dict = vac(chunk, return_seconds=False)\n",
" if speech_dict:\n",
" print(speech_dict)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"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": "3.11.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|