You're looking at a specific version of this model. Jump to the model overview.
zf-kbot /md-lc-asr-l40s-1:cc26b6e2
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 |
string
|
Audio file to transcribe (WAV, MP3, FLAC, M4A, OGG or other FFmpeg-supported audio).
|
|
| language |
None
|
Auto
|
Recognition language hint; Auto detects the language.
|
| mode |
None
|
offline
|
Offline or file-chunked streaming decode; files over 30 seconds use segmented streaming.
|
| context |
string
|
|
Optional topic or recognition context.
|
| hotwords |
string
|
|
Optional names or terms to add to the recognition context.
|
| channel |
None
|
mean
|
Mix channels or select the left/right channel.
|
| auto_gain |
boolean
|
True
|
Apply limited gain only to exceptionally quiet file audio.
|
| stream_chunk_ms |
None
|
160
|
Decode chunk length in milliseconds for streaming modes.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'audio_seconds': {'title': 'Audio Seconds', 'type': 'number'},
'language': {'title': 'Language', 'type': 'string'},
'quality_status': {'title': 'Quality Status', 'type': 'string'},
'result_json': {'format': 'uri',
'title': 'Result Json',
'type': 'string'},
'status': {'title': 'Status', 'type': 'string'},
'text': {'title': 'Text', 'type': 'string'},
'transcript_txt': {'format': 'uri',
'title': 'Transcript Txt',
'type': 'string'},
'truncated': {'title': 'Truncated', 'type': 'boolean'}},
'required': ['text',
'language',
'audio_seconds',
'status',
'quality_status',
'truncated',
'transcript_txt',
'result_json'],
'title': 'Output',
'type': 'object'}