Starstruk Logo MarkStarstruk

v6.2

alibaba/zvecv6.2Nov 6, 2025by snakers4

AI Summary

This release reworks the VAD training paradigm and improves overall stability and quality on edge cases, including unusual voices, child voices, and muted speech.

Key Highlights

  • VAD training paradigm reworked for better performance
  • Improved stability on out-of-distribution and rare data
  • Significant quality improvements for muted voices and low-quality phone calls

New Features

  • Fix type hint for min_silence_at_max_speech
  • Adamnsandle contributions
  • Overall slight quality improvement

Full Release Notes

- VAD training paradigm reworked;
- Overall slight quality improvement (no metrics update);
- Higher stability on OOD / rare / strange / unique data;
- Significant quality improvements on various known edge cases:
  - Unusual voices
  - Child voices
  - Cartoon voices
  - Muted voices
  - Muted speech
  - Lower quality phone calls

## What's Changed

* Fix type hint for min_silence_at_max_speech (float -> int) by @Purfview in https://github.com/snakers4/silero-vad/pull/714
* Adamnsandle by @adamnsandle in https://github.com/snakers4/silero-vad/pull/717
* Adamnsandle by @adamnsandle in https://github.com/snakers4/silero-vad/pull/719

**Full Changelog**: https://github.com/snakers4/silero-vad/compare/v6.1...v6.2