v6.2

charmbracelet/catwalkv6.2Nov 6, 2025by snakers4

AI Summary

This release reworks the VAD training paradigm and focuses on improving stability and quality specifically on edge cases, including unusual, child, and muted voices.

Key Highlights

VAD training paradigm reworked
Significant quality improvements on edge cases (unusual, child, cartoon, muted voices)
Higher stability on out-of-distribution (OOD) and rare data
Slight overall quality improvement

New Features

Improved handling of muted voices and speech
Improved handling of lower quality phone calls

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