You're looking at a specific version of this model. Jump to the model overview.
romanfurman6 /whisperx-multi-chunk:3762efca
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| audio_urls |
array
|
Array of public audio urls to process
|
|
| total_duration_seconds |
number
|
Total duration of the complete audio in seconds
|
|
| chunk_size_seconds |
number
|
Duration of each chunk in seconds (used for timestamp calculation). Latest chunk can be shorter, it will be calculated based on the total duration and the number of chunks.
|
|
| language |
string
|
ISO code of the language spoken in the audio, specify None to perform language detection
|
|
| language_detection_min_prob |
number
|
0.7
|
Minimum probability for recursive language detection
|
| language_detection_max_tries |
integer
|
5
|
Maximum retries for recursive language detection
|
| initial_prompt |
string
|
Optional text prompt for the first window
|
|
| batch_size |
integer
|
32
|
Parallelization of input audio transcription
|
| temperature |
number
|
0.2
|
Temperature to use for sampling
|
| vad_onset |
number
|
0.5
|
VAD onset threshold
|
| vad_offset |
number
|
0.363
|
VAD offset threshold
|
| align_output |
boolean
|
False
|
Whether to align output for word-level timestamps
|
| diarization |
boolean
|
False
|
Whether to perform diarization
|
| huggingface_access_token |
string
|
HuggingFace token for diarization
|
|
| min_speakers |
integer
|
Minimum number of speakers if diarization is activated
|
|
| max_speakers |
integer
|
Maximum number of speakers if diarization is activated
|
|
| debug |
boolean
|
True
|
Print debug information
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'detected_language': {'title': 'Detected Language',
'type': 'string'},
'processing_time': {'title': 'Processing Time',
'type': 'number'},
'segments': {'title': 'Segments'},
'total_chunks': {'title': 'Total Chunks', 'type': 'integer'}},
'required': ['segments',
'detected_language',
'total_chunks',
'processing_time'],
'title': 'Output',
'type': 'object'}