omega19t/ctc-forced-aligner

CTC forced alignment using Meta's MMS model. Aligns a known transcript to audio and returns word-level timestamps.

Public

21 runs

GitHub

Run omega19t/ctc-forced-aligner 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		Input audio file (MP3, WAV, etc.)
transcript	string		Plain text transcript to align against the audio. Speaker names and audio tags should be removed beforehand.
language	string	eng	Language code ISO 639-3 (e.g. eng, fra, deu, spa)

{
  "type": "object",
  "title": "Input",
  "required": [
    "audio_file",
    "transcript"
  ],
  "properties": {
    "language": {
      "type": "string",
      "title": "Language",
      "default": "eng",
      "x-order": 2,
      "description": "Language code ISO 639-3 (e.g. eng, fra, deu, spa)"
    },
    "audio_file": {
      "type": "string",
      "title": "Audio File",
      "format": "uri",
      "x-order": 0,
      "description": "Input audio file (MP3, WAV, etc.)"
    },
    "transcript": {
      "type": "string",
      "title": "Transcript",
      "x-order": 1,
      "description": "Plain text transcript to align against the audio. Speaker names and audio tags should be removed beforehand."
    }
  }
}

Output schema

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

Schema

{
  "title": "Output"
}