File size: 16,127 Bytes
8718761 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
{
"cells": [
{
"cell_type": "markdown",
"id": "13dc05a3-de12-4d7a-a926-e99d6d97826e",
"metadata": {},
"source": [
"## Using Stable-ts with any ASR"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5cfee322-ebca-4c23-87a4-a109a2f85203",
"metadata": {},
"outputs": [],
"source": [
"import stable_whisper\n",
"assert int(stable_whisper.__version__.replace('.', '')) >= 270, f\"Requires Stable-ts 2.7.0+. Current version is {stable_whisper.__version__}.\""
]
},
{
"cell_type": "markdown",
"id": "e6c2dab2-f4df-46f9-b2e8-94dd88522c7d",
"metadata": {},
"source": [
"<br />\n",
"\n",
"Stable-ts can be used for other ASR models or web APIs by wrapping them as a function then passing it as the first argument to `non_whisper.transcribe_any()`."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "7d32fa9f-a54c-4996-97c3-3b360230d029",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"def inference(audio, **kwargs) -> dict:\n",
" # run model/API \n",
" # return data as a dictionary\n",
" data = {}\n",
" return data"
]
},
{
"cell_type": "markdown",
"id": "856ef1fd-f489-42af-a90c-97323fd05a6b",
"metadata": {},
"source": [
"The data returned by the function must be one of the following:\n",
"- an instance of `WhisperResult` containing the data\n",
"- a dictionary in an appropriate mapping\n",
"- a path of JSON file containing data in an appropriate mapping"
]
},
{
"cell_type": "markdown",
"id": "bbdebdad-af1d-4077-8e99-20e767a0fd91",
"metadata": {},
"source": [
"Here are the 3 types of mappings:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "06bc4ce7-5117-4674-8eb9-c343c13c18bc",
"metadata": {},
"outputs": [],
"source": [
"#1:\n",
"essential_mapping = [\n",
" [ # 1st Segment\n",
" {'word': ' And', 'start': 0.0, 'end': 1.28}, \n",
" {'word': ' when', 'start': 1.28, 'end': 1.52}, \n",
" {'word': ' no', 'start': 1.52, 'end': 2.26}, \n",
" {'word': ' ocean,', 'start': 2.26, 'end': 2.68},\n",
" {'word': ' mountain,', 'start': 3.28, 'end': 3.58}\n",
" ], \n",
" [ # 2nd Segment\n",
" {'word': ' or', 'start': 4.0, 'end': 4.08}, \n",
" {'word': ' sky', 'start': 4.08, 'end': 4.56}, \n",
" {'word': ' could', 'start': 4.56, 'end': 4.84}, \n",
" {'word': ' contain', 'start': 4.84, 'end': 5.26}, \n",
" {'word': ' us,', 'start': 5.26, 'end': 6.27},\n",
" {'word': ' our', 'start': 6.27, 'end': 6.58}, \n",
" {'word': ' gaze', 'start': 6.58, 'end': 6.98}, \n",
" {'word': ' hungered', 'start': 6.98, 'end': 7.88}, \n",
" {'word': ' starward.', 'start': 7.88, 'end': 8.64}\n",
" ]\n",
"]"
]
},
{
"cell_type": "markdown",
"id": "b53bd812-2838-4f47-ab5f-5e729801aaee",
"metadata": {},
"source": [
"<br />\n",
"\n",
"If word timings are not available they can be omitted, but operations that can be performed on this data will be limited."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "8c6bf720-5bfd-4e79-90e7-7049a2ca1d3a",
"metadata": {},
"outputs": [],
"source": [
"#2:\n",
"no_word_mapping = [\n",
" {\n",
" 'start': 0.0, \n",
" 'end': 3.58, \n",
" 'text': ' And when no ocean, mountain,',\n",
" }, \n",
" {\n",
" 'start': 4.0, \n",
" 'end': 8.64, \n",
" 'text': ' or sky could contain us, our gaze hungered starward.', \n",
" }\n",
"]"
]
},
{
"cell_type": "markdown",
"id": "108e960f-8bd1-4d2a-92bf-cc8cb56f4615",
"metadata": {},
"source": [
"<br />\n",
"\n",
"Below is the full mapping for normal Stable-ts results. `None` takes the place of any omitted values except for `start`, `end`, and `text`/`word` which are required."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "2969aad2-c8bf-4043-8015-669a3102e158",
"metadata": {},
"outputs": [],
"source": [
"#3:\n",
"full_mapping = {\n",
" 'language': 'en',\n",
" 'text': ' And when no ocean, mountain, or sky could contain us, our gaze hungered starward.', \n",
" 'segments': [\n",
" {\n",
" 'seek': 0.0, \n",
" 'start': 0.0, \n",
" 'end': 3.58, \n",
" 'text': ' And when no ocean, mountain,', \n",
" 'tokens': [400, 562, 572, 7810, 11, 6937, 11], \n",
" 'temperature': 0.0, \n",
" 'avg_logprob': -0.48702024376910663, \n",
" 'compression_ratio': 1.0657894736842106, \n",
" 'no_speech_prob': 0.3386174440383911, \n",
" 'id': 0, \n",
" 'words': [\n",
" {'word': ' And', 'start': 0.04, 'end': 1.28, 'probability': 0.6481522917747498, 'tokens': [400]}, \n",
" {'word': ' when', 'start': 1.28, 'end': 1.52, 'probability': 0.9869539141654968, 'tokens': [562]}, \n",
" {'word': ' no', 'start': 1.52, 'end': 2.26, 'probability': 0.57384192943573, 'tokens': [572]}, \n",
" {'word': ' ocean,', 'start': 2.26, 'end': 2.68, 'probability': 0.9484889507293701, 'tokens': [7810, 11]},\n",
" {'word': ' mountain,', 'start': 3.28, 'end': 3.58, 'probability': 0.9581122398376465, 'tokens': [6937, 11]}\n",
" ]\n",
" }, \n",
" {\n",
" 'seek': 0.0, \n",
" 'start': 4.0, \n",
" 'end': 8.64, \n",
" 'text': ' or sky could contain us, our gaze hungered starward.', \n",
" 'tokens': [420, 5443, 727, 5304, 505, 11, 527, 24294, 5753, 4073, 3543, 1007, 13], \n",
" 'temperature': 0.0, \n",
" 'avg_logprob': -0.48702024376910663, \n",
" 'compression_ratio': 1.0657894736842106, \n",
" 'no_speech_prob': 0.3386174440383911, \n",
" 'id': 1, \n",
" 'words': [\n",
" {'word': ' or', 'start': 4.0, 'end': 4.08, 'probability': 0.9937937259674072, 'tokens': [420]}, \n",
" {'word': ' sky', 'start': 4.08, 'end': 4.56, 'probability': 0.9950089454650879, 'tokens': [5443]}, \n",
" {'word': ' could', 'start': 4.56, 'end': 4.84, 'probability': 0.9915681481361389, 'tokens': [727]}, \n",
" {'word': ' contain', 'start': 4.84, 'end': 5.26, 'probability': 0.898974597454071, 'tokens': [5304]}, \n",
" {'word': ' us,', 'start': 5.26, 'end': 6.27, 'probability': 0.999351441860199, 'tokens': [505, 11]},\n",
" {'word': ' our', 'start': 6.27, 'end': 6.58, 'probability': 0.9634224772453308, 'tokens': [527]}, \n",
" {'word': ' gaze', 'start': 6.58, 'end': 6.98, 'probability': 0.8934874534606934, 'tokens': [24294]}, \n",
" {'word': ' hungered', 'start': 6.98, 'end': 7.88, 'probability': 0.7424876093864441, 'tokens': [5753, 4073]}, \n",
" {'word': ' starward.', 'start': 7.88, 'end': 8.64, 'probability': 0.464096799492836, 'tokens': [3543, 1007, 13]}\n",
" ]\n",
" }\n",
" ]\n",
"}"
]
},
{
"cell_type": "markdown",
"id": "49d136e4-0f7d-4dcf-84f9-efb6f0eda491",
"metadata": {},
"source": [
"<br />\n",
"\n",
"The function must also have `audio` as a parameter."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "33f03286-69f9-4ae1-aec0-250fd92a8cb6",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"def inference(audio, **kwargs) -> dict:\n",
" # run model/API on the audio\n",
" # return data in a proper format\n",
" return essential_mapping"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "d6710eb5-5386-42cf-b6e7-02a84b5fad40",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"result = stable_whisper.transcribe_any(inference, './demo.wav', vad=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "6d7f9de6-5c9b-4c73-808d-640b13efb051",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0\n",
"00:00:01,122 --> 00:00:02,680\n",
"And when no ocean,\n",
"\n",
"1\n",
"00:00:03,280 --> 00:00:03,580\n",
"mountain,\n",
"\n",
"2\n",
"00:00:04,000 --> 00:00:06,046\n",
"or sky could contain us,\n",
"\n",
"3\n",
"00:00:06,402 --> 00:00:08,640\n",
"our gaze hungered starward.\n"
]
}
],
"source": [
"print(result.to_srt_vtt(word_level=False))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "be5a45e8-1b25-4a70-9af6-94bc5379fc7d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
" Transcribe an audio file using any ASR system.\n",
"\n",
" Parameters\n",
" ----------\n",
" inference_func: Callable\n",
" Function that runs ASR when provided the [audio] and return data in the appropriate format.\n",
" For format examples: https://github.com/jianfch/stable-ts/blob/main/examples/non-whisper.ipynb\n",
"\n",
" audio: Union[str, np.ndarray, torch.Tensor, bytes]\n",
" The path/URL to the audio file, the audio waveform, or bytes of audio file.\n",
"\n",
" audio_type: str\n",
" The type that [audio] needs to be for [inference_func]. (Default: Same type as [audio])\n",
"\n",
" Types:\n",
" None (default)\n",
" same type as [audio]\n",
"\n",
" 'str'\n",
" a path to the file\n",
" -if [audio] is a file and not audio preprocessing is done,\n",
" [audio] will be directly passed into [inference_func]\n",
" -if audio preprocessing is performed (from [demucs] and/or [only_voice_freq]),\n",
" the processed audio will be encoded into [temp_file] and then passed into [inference_func]\n",
"\n",
" 'byte'\n",
" bytes (used for APIs or to avoid writing any data to hard drive)\n",
" -if [audio] is file, the bytes of file is used\n",
" -if [audio] PyTorch tensor or NumPy array, the bytes of the [audio] encoded into WAV format is used\n",
"\n",
" 'torch'\n",
" a PyTorch tensor containing the audio waveform, in float32 dtype, on CPU\n",
"\n",
" 'numpy'\n",
" a NumPy array containing the audio waveform, in float32 dtype\n",
"\n",
" input_sr: int\n",
" The sample rate of [audio]. (Default: Auto-detected if [audio] is str/bytes)\n",
"\n",
" model_sr: int\n",
" The sample rate to resample the audio into for [inference_func]. (Default: Same as [input_sr])\n",
" Resampling is only performed when [model_sr] do not match the sample rate of the final audio due to:\n",
" -[input_sr] not matching\n",
" -sample rate changed due to audio preprocessing from [demucs]=True\n",
"\n",
" inference_kwargs: dict\n",
" Dictionary of arguments provided to [inference_func]. (Default: None)\n",
"\n",
" temp_file: str\n",
" Temporary path for the preprocessed audio when [audio_type]='str'. (Default: './_temp_stable-ts_audio_.wav')\n",
"\n",
" verbose: bool\n",
" Whether to display the text being decoded to the console. If True, displays all the details,\n",
" If False, displays progressbar. If None, does not display anything (Default: False)\n",
"\n",
" regroup: Union[bool, str]\n",
" Whether to regroup all words into segments with more natural boundaries. (Default: True)\n",
" Specify string for customizing the regrouping algorithm.\n",
" Ignored if [word_timestamps]=False.\n",
"\n",
" suppress_silence: bool\n",
" Whether to suppress timestamp where audio is silent at segment-level\n",
" and word-level if [suppress_word_ts]=True. (Default: True)\n",
"\n",
" suppress_word_ts: bool\n",
" Whether to suppress timestamps, if [suppress_silence]=True, where audio is silent at word-level. (Default: True)\n",
"\n",
" q_levels: int\n",
" Quantization levels for generating timestamp suppression mask; ignored if [vad]=true. (Default: 20)\n",
" Acts as a threshold to marking sound as silent.\n",
" Fewer levels will increase the threshold of volume at which to mark a sound as silent.\n",
"\n",
" k_size: int\n",
" Kernel size for avg-pooling waveform to generate timestamp suppression mask; ignored if [vad]=true. (Default: 5)\n",
" Recommend 5 or 3; higher sizes will reduce detection of silence.\n",
"\n",
" demucs: bool\n",
" Whether to preprocess the audio track with Demucs to isolate vocals/remove noise. (Default: False)\n",
" Demucs must be installed to use. Official repo: https://github.com/facebookresearch/demucs\n",
"\n",
" demucs_device: str\n",
" Device to use for demucs: 'cuda' or 'cpu'. (Default. 'cuda' if torch.cuda.is_available() else 'cpu')\n",
"\n",
" demucs_output: str\n",
" Path to save the vocals isolated by Demucs as WAV file. Ignored if [demucs]=False.\n",
" Demucs must be installed to use. Official repo: https://github.com/facebookresearch/demucs\n",
"\n",
" vad: bool\n",
" Whether to use Silero VAD to generate timestamp suppression mask. (Default: False)\n",
" Silero VAD requires PyTorch 1.12.0+. Official repo: https://github.com/snakers4/silero-vad\n",
"\n",
" vad_threshold: float\n",
" Threshold for detecting speech with Silero VAD. (Default: 0.35)\n",
" Low threshold reduces false positives for silence detection.\n",
"\n",
" vad_onnx: bool\n",
" Whether to use ONNX for Silero VAD. (Default: False)\n",
"\n",
" min_word_dur: float\n",
" Only allow suppressing timestamps that result in word durations greater than this value. (default: 0.1)\n",
"\n",
" only_voice_freq: bool\n",
" Whether to only use sound between 200 - 5000 Hz, where majority of human speech are. (Default: False)\n",
"\n",
" only_ffmpeg: bool\n",
" Whether to use only FFmpeg (and not yt-dlp) for URls. (Default: False)\n",
"\n",
" Returns\n",
" -------\n",
" An instance of WhisperResult.\n",
" \n"
]
}
],
"source": [
"print(stable_whisper.transcribe_any.__doc__)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a99ee627-6ab4-411d-ba27-d372d3647593",
"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": "3.8.15"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|