danielrosehill/whisper-hebrish

Fine-tune of Whisper Large (Turbo V3) specialised in accuracy for "code switching": English speech with Hebrew words

Public

1 run

Weights

Run danielrosehill/whisper-hebrish 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
task	None	transcribe	Task to perform: transcribe or translate
language	None	auto	Language of the audio
audio	string		Audio file to transcribe (Hebrew or English)
return_timestamps	boolean	False	Return timestamps for each segment

{
  "type": "object",
  "title": "Input",
  "required": [
    "audio"
  ],
  "properties": {
    "task": {
      "enum": [
        "transcribe",
        "translate"
      ],
      "type": "string",
      "title": "task",
      "description": "Task to perform: transcribe or translate",
      "default": "transcribe",
      "x-order": 1
    },
    "audio": {
      "type": "string",
      "title": "Audio",
      "format": "uri",
      "description": "Audio file to transcribe (Hebrew or English)"
    },
    "language": {
      "enum": [
        "hebrew",
        "english",
        "auto"
      ],
      "type": "string",
      "title": "language",
      "description": "Language of the audio",
      "default": "auto",
      "x-order": 2
    },
    "return_timestamps": {
      "type": "boolean",
      "title": "Return Timestamps",
      "default": false,
      "description": "Return timestamps for each segment"
    }
  }
}

Output schema

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

Schema

{
  "type": "object",
  "title": "Output",
  "additionalProperties": true
}