Skip to content

Significant changes to Puhti & Mahti authentication coming in April! Read about the SSH key and multi-factor authentication requirements.

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.

Whisper can be installed to a SD Desktop virtual machine with SD Software installer.

The version provided for 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 --threads 4