← Back to all generators
m1guelpf/whisper-subtitles
OfficialView on Replicate →
Generate subtitles from an audio file, using OpenAI's Whisper model.
Capabilities
No capability data available
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
audio_path* | string(uri) | Audio file to transcribe | — | — |
format | string | Whether to generate subtitles on the SRT or VTT format. | "vtt" | srtvtt |
model_name | string | Name of the Whisper model to use. | "base" | tiny.entinybase.enbasesmall.ensmallmedium.enmediumlarge |
audio_pathrequiredstringAudio file to transcribe
formatstringWhether to generate subtitles on the SRT or VTT format.
Default:
"vtt"srtvtt
model_namestringName of the Whisper model to use.
Default:
"base"tiny.entinybase.enbasesmall.ensmallmedium.enmediumlarge
Version:
7f686e243a96Updated: 7/25/202673.9K runs
cinemasetfree.com