suminhthanh/whisperx-custom

suminhthanh / whisperx-custom

Public
1.2K runs

Run suminhthanh/whisperx-custom with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

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		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
cdn_upload_url	string		CDN UPLOAD URL
cdn_download_url	string		CDN DOWNLOAD URL

{
  "type": "object",
  "title": "Input",
  "properties": {
    "url": {
      "type": "string",
      "title": "Url",
      "x-order": 1,
      "description": "URL of the audio file (if audio_file is not provided)"
    },
    "debug": {
      "type": "boolean",
      "title": "Debug",
      "default": false,
      "x-order": 15,
      "description": "Print out compute/inference times and memory usage information"
    },
    "language": {
      "type": "string",
      "title": "Language",
      "x-order": 2,
      "description": "ISO code of the language spoken in the audio, specify None to perform language detection"
    },
    "vad_onset": {
      "type": "number",
      "title": "Vad Onset",
      "default": 0.5,
      "x-order": 8,
      "description": "VAD onset"
    },
    "audio_file": {
      "type": "string",
      "title": "Audio File",
      "format": "uri",
      "x-order": 0,
      "description": "Audio file"
    },
    "batch_size": {
      "type": "integer",
      "title": "Batch Size",
      "default": 64,
      "x-order": 6,
      "description": "Parallelization of input audio transcription"
    },
    "chunk_size": {
      "type": "integer",
      "title": "Chunk Size",
      "default": 4,
      "x-order": 21,
      "description": "Chunk size"
    },
    "keep_audio": {
      "type": "boolean",
      "title": "Keep Audio",
      "default": false,
      "x-order": 16,
      "description": "Keep the downloaded audio file"
    },
    "vad_offset": {
      "type": "number",
      "title": "Vad Offset",
      "default": 0.363,
      "x-order": 9,
      "description": "VAD offset"
    },
    "deep_filter": {
      "type": "boolean",
      "title": "Deep Filter",
      "default": false,
      "x-order": 20,
      "description": "Deep filter"
    },
    "diarization": {
      "type": "boolean",
      "title": "Diarization",
      "default": false,
      "x-order": 11,
      "description": "Assign speaker ID labels"
    },
    "temperature": {
      "type": "number",
      "title": "Temperature",
      "default": 0,
      "x-order": 7,
      "description": "Temperature to use for sampling"
    },
    "align_output": {
      "type": "boolean",
      "title": "Align Output",
      "default": false,
      "x-order": 10,
      "description": "Aligns whisper output to get accurate word-level timestamps"
    },
    "max_speakers": {
      "type": "integer",
      "title": "Max Speakers",
      "x-order": 14,
      "description": "Maximum number of speakers if diarization is activated (leave blank if unknown)"
    },
    "min_speakers": {
      "type": "integer",
      "title": "Min Speakers",
      "x-order": 13,
      "description": "Minimum number of speakers if diarization is activated (leave blank if unknown)"
    },
    "cleanup_voice": {
      "type": "boolean",
      "title": "Cleanup Voice",
      "default": false,
      "x-order": 19,
      "description": "Cleanup voice"
    },
    "cdn_upload_url": {
      "type": "string",
      "title": "Cdn Upload Url",
      "x-order": 22,
      "description": "CDN UPLOAD URL"
    },
    "initial_prompt": {
      "type": "string",
      "title": "Initial Prompt",
      "x-order": 5,
      "description": "Optional text to provide as a prompt for the first window"
    },
    "openai_api_key": {
      "type": "string",
      "title": "Openai Api Key",
      "x-order": 17,
      "description": "OpenAI API key"
    },
    "cdn_download_url": {
      "type": "string",
      "title": "Cdn Download Url",
      "x-order": 23,
      "description": "CDN DOWNLOAD URL"
    },
    "is_get_video_info": {
      "type": "boolean",
      "title": "Is Get Video Info",
      "default": false,
      "x-order": 18,
      "description": "Get video info"
    },
    "huggingface_access_token": {
      "type": "string",
      "title": "Huggingface Access Token",
      "x-order": 12,
      "description": "To enable diarization, please enter your HuggingFace token (read). You need to accept the user agreement for the models specified in the README."
    },
    "language_detection_min_prob": {
      "type": "number",
      "title": "Language Detection Min Prob",
      "default": 0,
      "x-order": 3,
      "description": "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": {
      "type": "integer",
      "title": "Language Detection Max Tries",
      "default": 5,
      "x-order": 4,
      "description": "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."
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "object",
  "title": "Output",
  "required": [
    "detected_language"
  ],
  "properties": {
    "srt": {
      "title": "Srt"
    },
    "text": {
      "title": "Text"
    },
    "score": {
      "title": "Score"
    },
    "title": {
      "title": "Title"
    },
    "segments": {
      "title": "Segments"
    },
    "video_id": {
      "title": "Video Id"
    },
    "video_info": {
      "title": "Video Info"
    },
    "view_count": {
      "title": "View Count"
    },
    "detected_language": {
      "type": "string",
      "title": "Detected Language"
    }
  }
}