anotherjesse
/
whisper-updated
test of replicate.com/openai/whisper updated with more recent ubuntu/cudann
Run anotherjesse/whisper-updated 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)
|
base
Options: tiny, base, small, medium, large |
Choose a Whisper model.
|
| format |
string
(enum)
|
text
Options: text, srt, vtt |
Choose a format for the output.
|
| translate |
boolean
|
False
|
Translate the text to English when set to True
|
{
"type": "object",
"title": "Input",
"required": [
"audio"
],
"properties": {
"audio": {
"type": "string",
"title": "Audio",
"format": "uri",
"x-order": 0,
"description": "Audio file"
},
"model": {
"enum": [
"tiny",
"base",
"small",
"medium",
"large"
],
"type": "string",
"title": "model",
"description": "Choose a Whisper model.",
"default": "base",
"x-order": 1
},
"format": {
"enum": [
"text",
"srt",
"vtt"
],
"type": "string",
"title": "format",
"description": "Choose a format for the output.",
"default": "text",
"x-order": 2
},
"translate": {
"type": "boolean",
"title": "Translate",
"default": false,
"x-order": 3,
"description": "Translate the text to English when set to True"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "object",
"title": "ModelOutput",
"required": [
"detected_language",
"transcription"
],
"properties": {
"translation": {
"type": "string",
"title": "Translation"
},
"transcription": {
"type": "string",
"title": "Transcription"
},
"detected_language": {
"type": "string",
"title": "Detected Language"
}
}
}