viktorfa/whisperx-api – API reference

viktorfa / whisperx-api

Public
6 runs

Run viktorfa/whisperx-api 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	string		Audio file
model	string (enum)	large-v2 Options: tiny, base, small, medium, large-v2	Whisper model to use
align	boolean	True	Make word-level timestamps (Takes longer time)
num_speakers	integer	0	Identify speakers (0 to not diarize)
lang	string		Language (Empty for automatic)
batch_size	integer	16	Batch size
debug	boolean	False	Print out memory usage information.

{
  "type": "object",
  "title": "Input",
  "required": [
    "audio"
  ],
  "properties": {
    "lang": {
      "type": "string",
      "title": "Lang",
      "x-order": 4,
      "description": "Language (Empty for automatic)"
    },
    "align": {
      "type": "boolean",
      "title": "Align",
      "default": true,
      "x-order": 2,
      "description": "Make word-level timestamps (Takes longer time)"
    },
    "audio": {
      "type": "string",
      "title": "Audio",
      "format": "uri",
      "x-order": 0,
      "description": "Audio file"
    },
    "debug": {
      "type": "boolean",
      "title": "Debug",
      "default": false,
      "x-order": 6,
      "description": "Print out memory usage information."
    },
    "model": {
      "enum": [
        "tiny",
        "base",
        "small",
        "medium",
        "large-v2"
      ],
      "type": "string",
      "title": "model",
      "description": "Whisper model to use",
      "default": "large-v2",
      "x-order": 1
    },
    "batch_size": {
      "type": "integer",
      "title": "Batch Size",
      "default": 16,
      "x-order": 5,
      "description": "Batch size"
    },
    "num_speakers": {
      "type": "integer",
      "title": "Num Speakers",
      "default": 0,
      "x-order": 3,
      "description": "Identify speakers (0 to not diarize)"
    }
  }
}

Output schema

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

Schema

{
  "type": "object",
  "title": "Output",
  "required": [
    "jsonData",
    "text",
    "asrResult"
  ],
  "properties": {
    "text": {
      "type": "string",
      "title": "Text",
      "format": "uri"
    },
    "jsonData": {
      "type": "string",
      "title": "Jsondata"
    },
    "asrResult": {
      "type": "string",
      "title": "Asrresult",
      "format": "uri"
    },
    "alignResult": {
      "type": "string",
      "title": "Alignresult",
      "format": "uri"
    }
  }
}