v6.2

KalyanKS-NLP/llm-engineer-toolkitv6.2Nov 6, 2025by snakers4

AI Summary

Reworked the VAD training paradigm to improve stability on Out-of-Distribution (OOD) and rare data, with specific quality enhancements for challenging voice types.

Key Highlights

VAD training paradigm rework
Higher stability on OOD / rare / strange / unique data
Significant quality improvements on unusual, child, and muted voices
Improved handling of low-quality phone calls

New Features

VAD training paradigm rework
Edge case handling for unusual and cartoon voices
Muted speech and voice detection improvements
Stability improvements on rare data types

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