WhisperKit icon indicating copy to clipboard operation
WhisperKit copied to clipboard

Fix silence detection

Open aigerimmmm opened this issue 7 months ago • 4 comments

PR for the issue https://github.com/argmaxinc/WhisperKit/issues/27.

  • Added SilenceDetectionFilter similar to LanguageDetectionFilter.
  • Implemented detectSilence similar to detectLanguage in TextDecoder that does a single forward pass from to detect silence periods.
  • Added tests for SilenceDetectionFilter.
  • Added silence detection and segment skipping logic in TranscribeTask.
  • Updated models to support silence detection:
    • Added flags in DecodingOptions for ignoring prefill prompts during silence detection.
    • Changed property for managing silence detection threshold.

aigerimmmm avatar Jun 26 '24 08:06 aigerimmmm