Skip to content

Schemas

Models module of the Wordcab Transcribe.

AudioRequest

Bases: BaseRequest

Request model for the ASR audio file and url endpoint.

Source code in src/wordcab_transcribe/models.py 
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
class AudioRequest(BaseRequest):
    """Request model for the ASR audio file and url endpoint."""

    multi_channel: bool = False

    class Config:
        """Pydantic config class."""

        json_schema_extra = {
            "example": {
                "offset_start": None,
                "offset_end": None,
                "num_speakers": -1,
                "diarization": False,
                "source_lang": "en",
                "timestamps": "s",
                "vocab": [
                    "custom company name",
                    "custom product name",
                    "custom co-worker name",
                ],
                "word_timestamps": False,
                "internal_vad": False,
                "repetition_penalty": 1.2,
                "compression_ratio_threshold": 2.4,
                "log_prob_threshold": -1.0,
                "no_speech_threshold": 0.6,
                "condition_on_previous_text": True,
                "multi_channel": False,
            }
        }

Config

Pydantic config class.

Source code in src/wordcab_transcribe/models.py 
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
class Config:
    """Pydantic config class."""

    json_schema_extra = {
        "example": {
            "offset_start": None,
            "offset_end": None,
            "num_speakers": -1,
            "diarization": False,
            "source_lang": "en",
            "timestamps": "s",
            "vocab": [
                "custom company name",
                "custom product name",
                "custom co-worker name",
            ],
            "word_timestamps": False,
            "internal_vad": False,
            "repetition_penalty": 1.2,
            "compression_ratio_threshold": 2.4,
            "log_prob_threshold": -1.0,
            "no_speech_threshold": 0.6,
            "condition_on_previous_text": True,
            "multi_channel": False,
        }
    }

AudioResponse

Bases: BaseResponse

Response model for the ASR audio file and url endpoint.

Source code in src/wordcab_transcribe/models.py 
 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
class AudioResponse(BaseResponse):
    """Response model for the ASR audio file and url endpoint."""

    multi_channel: bool

    class Config:
        """Pydantic config class."""

        json_schema_extra = {
            "example": {
                "utterances": [
                    {
                        "text": "Hello World!",
                        "start": 0.345,
                        "end": 1.234,
                        "speaker": 0,
                    },
                    {
                        "text": "Wordcab is awesome",
                        "start": 1.234,
                        "end": 2.678,
                        "speaker": 1,
                    },
                ],
                "audio_duration": 2.678,
                "offset_start": None,
                "offset_end": None,
                "num_speakers": -1,
                "diarization": False,
                "source_lang": "en",
                "timestamps": "s",
                "vocab": [
                    "custom company name",
                    "custom product name",
                    "custom co-worker name",
                ],
                "word_timestamps": False,
                "internal_vad": False,
                "repetition_penalty": 1.2,
                "compression_ratio_threshold": 2.4,
                "log_prob_threshold": -1.0,
                "no_speech_threshold": 0.6,
                "condition_on_previous_text": True,
                "process_times": {
                    "total": 2.678,
                    "transcription": 2.439,
                    "diarization": None,
                    "post_processing": 0.239,
                },
                "multi_channel": False,
            }
        }

Config

Pydantic config class.

Source code in src/wordcab_transcribe/models.py 
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
class Config:
    """Pydantic config class."""

    json_schema_extra = {
        "example": {
            "utterances": [
                {
                    "text": "Hello World!",
                    "start": 0.345,
                    "end": 1.234,
                    "speaker": 0,
                },
                {
                    "text": "Wordcab is awesome",
                    "start": 1.234,
                    "end": 2.678,
                    "speaker": 1,
                },
            ],
            "audio_duration": 2.678,
            "offset_start": None,
            "offset_end": None,
            "num_speakers": -1,
            "diarization": False,
            "source_lang": "en",
            "timestamps": "s",
            "vocab": [
                "custom company name",
                "custom product name",
                "custom co-worker name",
            ],
            "word_timestamps": False,
            "internal_vad": False,
            "repetition_penalty": 1.2,
            "compression_ratio_threshold": 2.4,
            "log_prob_threshold": -1.0,
            "no_speech_threshold": 0.6,
            "condition_on_previous_text": True,
            "process_times": {
                "total": 2.678,
                "transcription": 2.439,
                "diarization": None,
                "post_processing": 0.239,
            },
            "multi_channel": False,
        }
    }

BaseRequest

Bases: BaseModel

Base request model for the API.

Source code in src/wordcab_transcribe/models.py 
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
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
class BaseRequest(BaseModel):
    """Base request model for the API."""

    offset_start: Union[float, None] = None
    offset_end: Union[float, None] = None
    num_speakers: int = -1
    diarization: bool = False
    source_lang: str = "en"
    timestamps: Timestamps = Timestamps.seconds
    vocab: Union[List[str], None] = None
    word_timestamps: bool = False
    internal_vad: bool = False
    repetition_penalty: float = 1.2
    compression_ratio_threshold: float = 2.4
    log_prob_threshold: float = -1.0
    no_speech_threshold: float = 0.6
    condition_on_previous_text: bool = True

    @field_validator("vocab")
    def validate_each_vocab_value(
        cls, value: Union[List[str], None]  # noqa: B902, N805
    ) -> List[str]:
        """Validate the value of each vocab field."""
        if value == []:
            return None
        elif value is not None and not all(isinstance(v, str) for v in value):
            raise ValueError("`vocab` must be a list of strings.")

        return value

    class Config:
        """Pydantic config class."""

        json_schema_extra = {
            "example": {
                "offset_start": None,
                "offset_end": None,
                "num_speakers": -1,
                "diarization": False,
                "source_lang": "en",
                "timestamps": "s",
                "vocab": [
                    "custom company name",
                    "custom product name",
                    "custom co-worker name",
                ],
                "word_timestamps": False,
                "internal_vad": False,
                "repetition_penalty": 1.2,
                "compression_ratio_threshold": 2.4,
                "log_prob_threshold": -1.0,
                "no_speech_threshold": 0.6,
                "condition_on_previous_text": True,
            }
        }

Config

Pydantic config class.

Source code in src/wordcab_transcribe/models.py 
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
class Config:
    """Pydantic config class."""

    json_schema_extra = {
        "example": {
            "offset_start": None,
            "offset_end": None,
            "num_speakers": -1,
            "diarization": False,
            "source_lang": "en",
            "timestamps": "s",
            "vocab": [
                "custom company name",
                "custom product name",
                "custom co-worker name",
            ],
            "word_timestamps": False,
            "internal_vad": False,
            "repetition_penalty": 1.2,
            "compression_ratio_threshold": 2.4,
            "log_prob_threshold": -1.0,
            "no_speech_threshold": 0.6,
            "condition_on_previous_text": True,
        }
    }

validate_each_vocab_value(value)

Validate the value of each vocab field.

Source code in src/wordcab_transcribe/models.py 
410
411
412
413
414
415
416
417
418
419
420
@field_validator("vocab")
def validate_each_vocab_value(
    cls, value: Union[List[str], None]  # noqa: B902, N805
) -> List[str]:
    """Validate the value of each vocab field."""
    if value == []:
        return None
    elif value is not None and not all(isinstance(v, str) for v in value):
        raise ValueError("`vocab` must be a list of strings.")

    return value

BaseResponse

Bases: BaseModel

Base response model, not meant to be used directly.

Source code in src/wordcab_transcribe/models.py 
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
class BaseResponse(BaseModel):
    """Base response model, not meant to be used directly."""

    utterances: List[Utterance]
    audio_duration: float
    offset_start: Union[float, None]
    offset_end: Union[float, None]
    num_speakers: int
    diarization: bool
    source_lang: str
    timestamps: str
    vocab: Union[List[str], None]
    word_timestamps: bool
    internal_vad: bool
    repetition_penalty: float
    compression_ratio_threshold: float
    log_prob_threshold: float
    no_speech_threshold: float
    condition_on_previous_text: bool
    process_times: ProcessTimes

CortexError

Bases: BaseModel

Error model for the Cortex API.

Source code in src/wordcab_transcribe/models.py 
206
207
208
209
210
211
212
213
214
215
216
217
218
class CortexError(BaseModel):
    """Error model for the Cortex API."""

    message: str

    class Config:
        """Pydantic config class."""

        json_schema_extra = {
            "example": {
                "message": "Error message here",
            }
        }

Config

Pydantic config class.

Source code in src/wordcab_transcribe/models.py 
211
212
213
214
215
216
217
218
class Config:
    """Pydantic config class."""

    json_schema_extra = {
        "example": {
            "message": "Error message here",
        }
    }

CortexPayload

Bases: BaseModel

Request object for Cortex endpoint.

Source code in src/wordcab_transcribe/models.py 
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
class CortexPayload(BaseModel):
    """Request object for Cortex endpoint."""

    url_type: Literal["audio_url", "youtube"]
    url: Optional[str] = None
    api_key: Optional[str] = None
    offset_start: Optional[float] = None
    offset_end: Optional[float] = None
    num_speakers: Optional[int] = -1
    diarization: Optional[bool] = False
    multi_channel: Optional[bool] = False
    source_lang: Optional[str] = "en"
    timestamps: Optional[Timestamps] = Timestamps.seconds
    vocab: Union[List[str], None] = None
    word_timestamps: Optional[bool] = False
    internal_vad: Optional[bool] = False
    repetition_penalty: Optional[float] = 1.2
    compression_ratio_threshold: Optional[float] = 2.4
    log_prob_threshold: Optional[float] = -1.0
    no_speech_threshold: Optional[float] = 0.6
    condition_on_previous_text: Optional[bool] = True
    job_name: Optional[str] = None
    ping: Optional[bool] = False

    class Config:
        """Pydantic config class."""

        json_schema_extra = {
            "example": {
                "url_type": "youtube",
                "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
                "api_key": "1234567890",
                "offset_start": None,
                "offset_end": None,
                "num_speakers": -1,
                "diarization": False,
                "multi_channel": False,
                "source_lang": "en",
                "timestamps": "s",
                "vocab": [
                    "custom company name",
                    "custom product name",
                    "custom co-worker name",
                ],
                "word_timestamps": False,
                "internal_vad": False,
                "repetition_penalty": 1.2,
                "compression_ratio_threshold": 2.4,
                "log_prob_threshold": -1.0,
                "no_speech_threshold": 0.6,
                "condition_on_previous_text": True,
                "job_name": "job_abc123",
                "ping": False,
            }
        }

Config

Pydantic config class.

Source code in src/wordcab_transcribe/models.py 
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
class Config:
    """Pydantic config class."""

    json_schema_extra = {
        "example": {
            "url_type": "youtube",
            "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
            "api_key": "1234567890",
            "offset_start": None,
            "offset_end": None,
            "num_speakers": -1,
            "diarization": False,
            "multi_channel": False,
            "source_lang": "en",
            "timestamps": "s",
            "vocab": [
                "custom company name",
                "custom product name",
                "custom co-worker name",
            ],
            "word_timestamps": False,
            "internal_vad": False,
            "repetition_penalty": 1.2,
            "compression_ratio_threshold": 2.4,
            "log_prob_threshold": -1.0,
            "no_speech_threshold": 0.6,
            "condition_on_previous_text": True,
            "job_name": "job_abc123",
            "ping": False,
        }
    }

CortexUrlResponse

Bases: AudioResponse

Response model for the audio_url type of the Cortex endpoint.

Source code in src/wordcab_transcribe/models.py 
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
class CortexUrlResponse(AudioResponse):
    """Response model for the audio_url type of the Cortex endpoint."""

    job_name: str
    request_id: Optional[str] = None

    class Config:
        """Pydantic config class."""

        json_schema_extra = {
            "example": {
                "utterances": [
                    {
                        "speaker": 0,
                        "start": 0.0,
                        "end": 1.0,
                        "text": "Hello World!",
                    },
                    {
                        "speaker": 0,
                        "start": 1.0,
                        "end": 2.0,
                        "text": "Wordcab is awesome",
                    },
                ],
                "audio_duration": 2.0,
                "offset_start": None,
                "offset_end": None,
                "num_speakers": -1,
                "diarization": False,
                "source_lang": "en",
                "timestamps": "s",
                "vocab": [
                    "custom company name",
                    "custom product name",
                    "custom co-worker name",
                ],
                "word_timestamps": False,
                "internal_vad": False,
                "repetition_penalty": 1.2,
                "compression_ratio_threshold": 2.4,
                "log_prob_threshold": -1.0,
                "no_speech_threshold": 0.6,
                "condition_on_previous_text": True,
                "process_times": {
                    "total": 2.678,
                    "transcription": 2.439,
                    "diarization": None,
                    "post_processing": 0.239,
                },
                "multi_channel": False,
                "job_name": "job_name",
                "request_id": "request_id",
            }
        }

Config

Pydantic config class.

Source code in src/wordcab_transcribe/models.py 
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
class Config:
    """Pydantic config class."""

    json_schema_extra = {
        "example": {
            "utterances": [
                {
                    "speaker": 0,
                    "start": 0.0,
                    "end": 1.0,
                    "text": "Hello World!",
                },
                {
                    "speaker": 0,
                    "start": 1.0,
                    "end": 2.0,
                    "text": "Wordcab is awesome",
                },
            ],
            "audio_duration": 2.0,
            "offset_start": None,
            "offset_end": None,
            "num_speakers": -1,
            "diarization": False,
            "source_lang": "en",
            "timestamps": "s",
            "vocab": [
                "custom company name",
                "custom product name",
                "custom co-worker name",
            ],
            "word_timestamps": False,
            "internal_vad": False,
            "repetition_penalty": 1.2,
            "compression_ratio_threshold": 2.4,
            "log_prob_threshold": -1.0,
            "no_speech_threshold": 0.6,
            "condition_on_previous_text": True,
            "process_times": {
                "total": 2.678,
                "transcription": 2.439,
                "diarization": None,
                "post_processing": 0.239,
            },
            "multi_channel": False,
            "job_name": "job_name",
            "request_id": "request_id",
        }
    }

CortexYoutubeResponse

Bases: YouTubeResponse

Response model for the YouTube type of the Cortex endpoint.

Source code in src/wordcab_transcribe/models.py 
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
class CortexYoutubeResponse(YouTubeResponse):
    """Response model for the YouTube type of the Cortex endpoint."""

    job_name: str
    request_id: Optional[str] = None

    class Config:
        """Pydantic config class."""

        json_schema_extra = {
            "example": {
                "utterances": [
                    {
                        "speaker": 0,
                        "start": 0.0,
                        "end": 1.0,
                        "text": "Never gonna give you up!",
                    },
                    {
                        "speaker": 0,
                        "start": 1.0,
                        "end": 2.0,
                        "text": "Never gonna let you down!",
                    },
                ],
                "audio_duration": 2.0,
                "offset_start": None,
                "offset_end": None,
                "num_speakers": -1,
                "diarization": False,
                "source_lang": "en",
                "timestamps": "s",
                "vocab": [
                    "custom company name",
                    "custom product name",
                    "custom co-worker name",
                ],
                "word_timestamps": False,
                "internal_vad": False,
                "repetition_penalty": 1.2,
                "compression_ratio_threshold": 2.4,
                "log_prob_threshold": -1.0,
                "no_speech_threshold": 0.6,
                "condition_on_previous_text": True,
                "process_times": {
                    "total": 2.678,
                    "transcription": 2.439,
                    "diarization": None,
                    "post_processing": 0.239,
                },
                "video_url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
                "job_name": "job_name",
                "request_id": "request_id",
            }
        }

Config

Pydantic config class.

Source code in src/wordcab_transcribe/models.py 
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
class Config:
    """Pydantic config class."""

    json_schema_extra = {
        "example": {
            "utterances": [
                {
                    "speaker": 0,
                    "start": 0.0,
                    "end": 1.0,
                    "text": "Never gonna give you up!",
                },
                {
                    "speaker": 0,
                    "start": 1.0,
                    "end": 2.0,
                    "text": "Never gonna let you down!",
                },
            ],
            "audio_duration": 2.0,
            "offset_start": None,
            "offset_end": None,
            "num_speakers": -1,
            "diarization": False,
            "source_lang": "en",
            "timestamps": "s",
            "vocab": [
                "custom company name",
                "custom product name",
                "custom co-worker name",
            ],
            "word_timestamps": False,
            "internal_vad": False,
            "repetition_penalty": 1.2,
            "compression_ratio_threshold": 2.4,
            "log_prob_threshold": -1.0,
            "no_speech_threshold": 0.6,
            "condition_on_previous_text": True,
            "process_times": {
                "total": 2.678,
                "transcription": 2.439,
                "diarization": None,
                "post_processing": 0.239,
            },
            "video_url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
            "job_name": "job_name",
            "request_id": "request_id",
        }
    }

DiarizationOutput

Bases: BaseModel

Diarization output model for the API.

Source code in src/wordcab_transcribe/models.py 
512
513
514
515
class DiarizationOutput(BaseModel):
    """Diarization output model for the API."""

    segments: List[DiarizationSegment]

DiarizationRequest

Bases: BaseModel

Request model for the diarize endpoint.

Source code in src/wordcab_transcribe/models.py 
518
519
520
521
522
523
class DiarizationRequest(BaseModel):
    """Request model for the diarize endpoint."""

    audio: TensorShare
    duration: float
    num_speakers: int

DiarizationSegment

Bases: NamedTuple

Diarization segment model for the API.

Source code in src/wordcab_transcribe/models.py 
504
505
506
507
508
509
class DiarizationSegment(NamedTuple):
    """Diarization segment model for the API."""

    start: float
    end: float
    speaker: int

MultiChannelSegment

Bases: NamedTuple

Multi-channel segment model for the API.

Source code in src/wordcab_transcribe/models.py 
56
57
58
59
60
61
62
63
class MultiChannelSegment(NamedTuple):
    """Multi-channel segment model for the API."""

    start: float
    end: float
    text: str
    words: List[Word]
    speaker: int

MultiChannelTranscriptionOutput

Bases: BaseModel

Multi-channel transcription output model for the API.

Source code in src/wordcab_transcribe/models.py 
526
527
528
529
class MultiChannelTranscriptionOutput(BaseModel):
    """Multi-channel transcription output model for the API."""

    segments: List[MultiChannelSegment]

PongResponse

Bases: BaseModel

Response model for the ping endpoint.

Source code in src/wordcab_transcribe/models.py 
482
483
484
485
486
487
488
489
490
491
492
493
494
class PongResponse(BaseModel):
    """Response model for the ping endpoint."""

    message: str

    class Config:
        """Pydantic config class."""

        json_schema_extra = {
            "example": {
                "message": "pong",
            },
        }

Config

Pydantic config class.

Source code in src/wordcab_transcribe/models.py 
487
488
489
490
491
492
493
494
class Config:
    """Pydantic config class."""

    json_schema_extra = {
        "example": {
            "message": "pong",
        },
    }

ProcessTimes

Bases: BaseModel

The execution times of the different processes.

Source code in src/wordcab_transcribe/models.py 
30
31
32
33
34
35
36
class ProcessTimes(BaseModel):
    """The execution times of the different processes."""

    total: Union[float, None] = None
    transcription: Union[float, None] = None
    diarization: Union[float, None] = None
    post_processing: Union[float, None] = None

Timestamps

Bases: str, Enum

Timestamps enum for the API.

Source code in src/wordcab_transcribe/models.py 
39
40
41
42
43
44
class Timestamps(str, Enum):
    """Timestamps enum for the API."""

    seconds = "s"
    milliseconds = "ms"
    hour_minute_second = "hms"

Token

Bases: BaseModel

Token model for authentication.

Source code in src/wordcab_transcribe/models.py 
552
553
554
555
556
class Token(BaseModel):
    """Token model for authentication."""

    access_token: str
    token_type: str

TokenData

Bases: BaseModel

TokenData model for authentication.

Source code in src/wordcab_transcribe/models.py 
559
560
561
562
class TokenData(BaseModel):
    """TokenData model for authentication."""

    username: Optional[str] = None

TranscribeRequest

Bases: BaseModel

Request model for the transcribe endpoint.

Source code in src/wordcab_transcribe/models.py 
538
539
540
541
542
543
544
545
546
547
548
549
class TranscribeRequest(BaseModel):
    """Request model for the transcribe endpoint."""

    audio: Union[TensorShare, List[TensorShare]]
    compression_ratio_threshold: float
    condition_on_previous_text: bool
    internal_vad: bool
    log_prob_threshold: float
    no_speech_threshold: float
    repetition_penalty: float
    source_lang: str
    vocab: Union[List[str], None]

TranscriptionOutput

Bases: BaseModel

Transcription output model for the API.

Source code in src/wordcab_transcribe/models.py 
532
533
534
535
class TranscriptionOutput(BaseModel):
    """Transcription output model for the API."""

    segments: List[Segment]

UrlSchema

Bases: BaseModel

Request model for the add_url endpoint.

Source code in src/wordcab_transcribe/models.py 
497
498
499
500
501
class UrlSchema(BaseModel):
    """Request model for the add_url endpoint."""

    task: Literal["transcription", "diarization"]
    url: HttpUrl

Utterance

Bases: BaseModel

Utterance model for the API.

Source code in src/wordcab_transcribe/models.py 
66
67
68
69
70
71
72
73
class Utterance(BaseModel):
    """Utterance model for the API."""

    text: str
    start: Union[float, str]
    end: Union[float, str]
    speaker: Union[int, None] = None
    words: Union[List[Word], None] = None

Word

Bases: BaseModel

Word model for the API.

Source code in src/wordcab_transcribe/models.py 
47
48
49
50
51
52
53
class Word(BaseModel):
    """Word model for the API."""

    word: str
    start: float
    end: float
    probability: float

YouTubeResponse

Bases: BaseResponse

Response model for the ASR YouTube endpoint.

Source code in src/wordcab_transcribe/models.py 
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
class YouTubeResponse(BaseResponse):
    """Response model for the ASR YouTube endpoint."""

    video_url: str

    class Config:
        """Pydantic config class."""

        json_schema_extra = {
            "example": {
                "utterances": [
                    {
                        "speaker": 0,
                        "start": 0.0,
                        "end": 1.0,
                        "text": "Never gonna give you up!",
                    },
                    {
                        "speaker": 0,
                        "start": 1.0,
                        "end": 2.0,
                        "text": "Never gonna let you down!",
                    },
                ],
                "audio_duration": 2.0,
                "offset_start": None,
                "offset_end": None,
                "num_speakers": -1,
                "diarization": False,
                "source_lang": "en",
                "timestamps": "s",
                "vocab": [
                    "custom company name",
                    "custom product name",
                    "custom co-worker name",
                ],
                "word_timestamps": False,
                "internal_vad": False,
                "repetition_penalty": 1.2,
                "compression_ratio_threshold": 2.4,
                "log_prob_threshold": -1.0,
                "no_speech_threshold": 0.6,
                "condition_on_previous_text": True,
                "process_times": {
                    "total": 2.678,
                    "transcription": 2.439,
                    "diarization": None,
                    "post_processing": 0.239,
                },
                "video_url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
            }
        }

Config

Pydantic config class.

Source code in src/wordcab_transcribe/models.py 
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
class Config:
    """Pydantic config class."""

    json_schema_extra = {
        "example": {
            "utterances": [
                {
                    "speaker": 0,
                    "start": 0.0,
                    "end": 1.0,
                    "text": "Never gonna give you up!",
                },
                {
                    "speaker": 0,
                    "start": 1.0,
                    "end": 2.0,
                    "text": "Never gonna let you down!",
                },
            ],
            "audio_duration": 2.0,
            "offset_start": None,
            "offset_end": None,
            "num_speakers": -1,
            "diarization": False,
            "source_lang": "en",
            "timestamps": "s",
            "vocab": [
                "custom company name",
                "custom product name",
                "custom co-worker name",
            ],
            "word_timestamps": False,
            "internal_vad": False,
            "repetition_penalty": 1.2,
            "compression_ratio_threshold": 2.4,
            "log_prob_threshold": -1.0,
            "no_speech_threshold": 0.6,
            "condition_on_previous_text": True,
            "process_times": {
                "total": 2.678,
                "transcription": 2.439,
                "diarization": None,
                "post_processing": 0.239,
            },
            "video_url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
        }
    }
Last update: 2023-10-12
Created: 2023-10-12