Models / openai / Whisper Small

Whisper Small

openaiaudio

A compact Whisper model for multilingual speech recognition with 244M parameters.

audiostreaming

homepage ↗docs ↗

Specs

Context & limits

—

context window

—

max output

Lifecycle

Dates

released2022-09-01

Aliases

Also known as

whisper-small

Resources

homepagehttps://github.com/openai/whisper ↗

docshttps://platform.openai.com/docs/guides/speech-to-text ↗