You're looking at a specific version of this model. Jump to the model overview.
rafaelgalle /whisper-diarization-advanced:7dfeffa3
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 |
|---|---|---|---|
| prompt |
string
|
Names/acronyms, separated by punctuation
|
|
| file_url |
string
|
Direct URL
|
|
| language |
string
|
Language code like 'en', 'pt'
|
|
| file_path |
string
|
Audio file
|
|
| translate |
boolean
|
False
|
Translate to English
|
| preprocess |
integer
|
0
Max: 4 |
0=None, 1=Sanitize, 2=+Filter, 3=+ReduceNoise, 4=+Normalize
|
| stationary |
boolean
|
True
|
None
|
| file_string |
string
|
Base64 audio
|
|
| target_dBFS |
number
|
-18
|
None
|
| lowpass_freq |
integer
|
8000
|
None
|
| num_speakers |
integer
|
Min: 1 Max: 50 |
Leave empty to autodetect
|
| highpass_freq |
integer
|
45
|
None
|
| prop_decrease |
number
|
0.3
|
None
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'language': {'title': 'Language', 'type': 'string'},
'metrics': {'additionalProperties': True,
'title': 'Metrics',
'type': 'object'},
'num_speakers': {'title': 'Num Speakers', 'type': 'integer'},
'segments': {'items': {},
'title': 'Segments',
'type': 'array'}},
'required': ['segments', 'metrics'],
'title': 'Output',
'type': 'object'}