You're looking at a specific version of this model. Jump to the model overview.
suminhthanh /whisperx-custom:4b17e12b
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_file |
string
|
Audio file
|
|
| url |
string
|
URL of the audio file (if audio_file is not provided)
|
|
| language |
string
|
vi
|
ISO code of the language spoken in the audio, specify None to perform language detection
|
| language_detection_min_prob |
number
|
0
|
If language is not specified, then the language will be detected recursively on different parts of the file until it reaches the given probability
|
| language_detection_max_tries |
integer
|
5
|
If language is not specified, then the language will be detected following the logic of language_detection_min_prob parameter, but will stop after the given max retries. If max retries is reached, the most probable language is kept.
|
| initial_prompt |
string
|
Optional text to provide as a prompt for the first window
|
|
| batch_size |
integer
|
64
|
Parallelization of input audio transcription
|
| temperature |
number
|
0
|
Temperature to use for sampling
|
| vad_onset |
number
|
0.5
|
VAD onset
|
| vad_offset |
number
|
0.363
|
VAD offset
|
| align_output |
boolean
|
False
|
Aligns whisper output to get accurate word-level timestamps
|
| diarization |
boolean
|
False
|
Assign speaker ID labels
|
| huggingface_access_token |
string
|
To enable diarization, please enter your HuggingFace token (read). You need to accept the user agreement for the models specified in the README.
|
|
| min_speakers |
integer
|
Minimum number of speakers if diarization is activated (leave blank if unknown)
|
|
| max_speakers |
integer
|
Maximum number of speakers if diarization is activated (leave blank if unknown)
|
|
| debug |
boolean
|
False
|
Print out compute/inference times and memory usage information
|
| keep_audio |
boolean
|
False
|
Keep the downloaded audio file
|
| openai_api_key |
string
|
OpenAI API key
|
|
| is_get_video_info |
boolean
|
False
|
Get video info
|
| cleanup_voice |
boolean
|
False
|
Cleanup voice
|
| deep_filter |
boolean
|
False
|
Deep filter
|
| chunk_size |
integer
|
4
|
Chunk size
|
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'},
'score': {'title': 'Score'},
'segments': {'title': 'Segments'},
'srt': {'format': 'uri', 'title': 'Srt', 'type': 'string'},
'text': {'title': 'Text'},
'title': {'title': 'Title'},
'video_id': {'title': 'Video Id'},
'video_info': {'title': 'Video Info'},
'view_count': {'title': 'View Count'}},
'required': ['detected_language', 'srt'],
'title': 'Output',
'type': 'object'}