github QuentinFuxa/WhisperLiveKit 0.2.8

latest releases: 0.2.17, 0.2.16, 0.2.15...
3 months ago

Dependency and Compatibility Changes

  • Removed Triton <3 requirement
  • Tested compatibility with Python 3.14 and 3.15

Performance Improvements

  • Simulstreaming backend now defaults to MLX-Whisper (if available) or Faster-Whisper (if available) encoders, paired with Whisper cross-attention and decoder using an AlignAtt policy, for increased speed. Can be disabled using --disable-fast-encoder
  • Encoders are loaded once and shared in Simulstreaming, reducing vRAM usage
  • Only the decoder of Whisper is loaded when using a different encoder, reducing vRAM usage

Frontend Enhancements

  • Added a microphone picker
  • Loads the UI as a single inline HTML file (instead of separate CSS, JS, SVGs and HTML files) for simplified deployment

Bug Fixes and Improvements

  • Resolved warmup error when no connection is provided or when the language is set to auto
  • Added pip timeout and retries in Dockerfile when installing Torch/TorchVision/TorchAudio
  • Fixed issue where an exception is raised when language is set to 'auto' and task is set to 'translation'
  • Enabled auto-detection of language for warmup if not specified

Don't miss a new WhisperLiveKit release

NewReleases is sending notifications on new releases.