Starstruk Logo MarkStarstruk

0.1.9

QuentinFuxa/WhisperLiveKit0.1.9Jun 19, 2025by QuentinFuxa

AI Summary

Optimizes diarization performance and introduces punctuation-based speaker splitting for more natural transitions.

Key Highlights

  • Improved diarization speed with buffering logic and fixed-size audio chunks.
  • Introduced punctuation-based speaker splitting beta feature.
  • Allows users to specify custom diarization models.

New Features

  • Faster diarization
  • Punctuation-based speaker splitting
  • Custom diarization models support

Full Release Notes

**Faster Diarization, Smarter Speaker Splitting**
- **Faster diarization**, with buffering logic and fixed-size audio chunks, now aligned with --min-chunk-size for improved real-time performance
- **Punctuation-based speaker splitting (beta)**: enables more natural transitions using --punctuation-split
- **Custom diarization models**: use --segmentation-model and --embedding-model to specify alternate backends. See [here](https://github.com/juanmc2005/diart/tree/main?tab=readme-ov-file#pre-trained-models) to get a list of available models