zf-kbot/md-lc-asr-l40s-1

Public

1 run

Run zf-kbot/md-lc-asr-l40s-1 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 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.

{
  "type": "object",
  "title": "Input",
  "required": [
    "audio"
  ],
  "properties": {
    "mode": {
      "enum": [
        "offline",
        "stream"
      ],
      "type": "string",
      "title": "mode",
      "description": "Offline or file-chunked streaming decode; files over 30 seconds use segmented streaming.",
      "default": "offline",
      "x-order": 2
    },
    "audio": {
      "type": "string",
      "title": "Audio",
      "format": "uri",
      "x-order": 0,
      "description": "Audio file to transcribe (WAV, MP3, FLAC, M4A, OGG or other FFmpeg-supported audio)."
    },
    "channel": {
      "enum": [
        "mean",
        "left",
        "right"
      ],
      "type": "string",
      "title": "channel",
      "description": "Mix channels or select the left/right channel.",
      "default": "mean",
      "x-order": 5
    },
    "context": {
      "type": "string",
      "title": "Context",
      "default": "",
      "x-order": 3,
      "description": "Optional topic or recognition context."
    },
    "hotwords": {
      "type": "string",
      "title": "Hotwords",
      "default": "",
      "x-order": 4,
      "description": "Optional names or terms to add to the recognition context."
    },
    "language": {
      "enum": [
        "Auto",
        "Chinese",
        "English",
        "Cantonese",
        "Japanese",
        "Korean",
        "German",
        "French",
        "Russian",
        "Portuguese",
        "Spanish",
        "Italian"
      ],
      "type": "string",
      "title": "language",
      "description": "Recognition language hint; Auto detects the language.",
      "default": "Auto",
      "x-order": 1
    },
    "auto_gain": {
      "type": "boolean",
      "title": "Auto Gain",
      "default": true,
      "x-order": 6,
      "description": "Apply limited gain only to exceptionally quiet file audio."
    },
    "stream_chunk_ms": {
      "enum": [
        160,
        320,
        480,
        640
      ],
      "type": "integer",
      "title": "stream_chunk_ms",
      "description": "Decode chunk length in milliseconds for streaming modes.",
      "default": 160,
      "x-order": 7
    }
  }
}

Output schema

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

Schema

{
  "type": "object",
  "title": "Output",
  "required": [
    "text",
    "language",
    "audio_seconds",
    "status",
    "quality_status",
    "truncated",
    "transcript_txt",
    "result_json"
  ],
  "properties": {
    "text": {
      "type": "string",
      "title": "Text"
    },
    "status": {
      "type": "string",
      "title": "Status"
    },
    "language": {
      "type": "string",
      "title": "Language"
    },
    "truncated": {
      "type": "boolean",
      "title": "Truncated"
    },
    "result_json": {
      "type": "string",
      "title": "Result Json",
      "format": "uri"
    },
    "audio_seconds": {
      "type": "number",
      "title": "Audio Seconds"
    },
    "quality_status": {
      "type": "string",
      "title": "Quality Status"
    },
    "transcript_txt": {
      "type": "string",
      "title": "Transcript Txt",
      "format": "uri"
    }
  }
}