Skip to content

Whisper

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.

The installation in SD Desktop is based on WhisperDO

After installation Whisper is available as a command line tool in SD Desktop. Sample command:

   whisper audio.mp3 --model medium