v6.2

siyuan-note/siyuanv6.2Nov 6, 2025by snakers4

AI Summary

This release reworks the VAD training paradigm to enhance overall stability and quality, specifically targeting difficult edge cases such as muted speech and unusual voices.

Key Highlights

Reworked VAD training paradigm
Improved stability on rare/unique data
Significant improvements for muted voices and speech
Better handling of lower quality phone calls
Fixed type hints for parameters

New Features

Edge case handling improvements
Training paradigm rework
Bug fixes for type hints

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