v6.2

camel-ai/camelv6.2Nov 6, 2025by snakers4

AI Summary

Improves voice activity detection quality on edge cases including unusual voices, child voices, and muted speech through a reworked training paradigm.

Key Highlights

Reworked VAD training paradigm for better stability.
Significant quality improvements on unusual, child, and cartoon voices.
Enhanced stability on Out-Of-Distribution (OOD) and rare data.
Better handling of muted voices and lower quality phone calls.

New Features

VAD training paradigm rework
Edge case handling improvements
Quality improvements for muted and low-quality speech

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