soykertje / whisper

Convert speech in audio to text

  • Public
  • 18.9K runs
  • GitHub
  • License

Whisper is a general-purpose speech transcription model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech transcription as well as speech translation and language identification.

This version uses the lasts whisper version available and add a new input to perform the transcription.