v0.2.22

MagicMirrorOrg/MagicMirrorv0.2.22Jun 4, 2026by QuentinFuxa

AI Summary

This release introduces core improvements to audio processing, specifically focusing on language handling, event management, and optimization of CUDA cache management.

Key Highlights

  • Normalized Whisper Chinese language codes (zh -> zh-CN)
  • Improved VAD event handling to prevent timestamp drift
  • Optimized CUDA cache cleanup for lightweight operations

New Features

  • NLLW language aliases normalization
  • VAD event handling improvements
  • CUDA cache cleanup optimization

Full Release Notes

## Core
- **NLLW language aliases** : Normalize Whisper Chinese language codes at the NLLW boundary (`zh` -> `zh-CN`) for transcription and translation configs
- **VAD event handling** : Preserve short silence boundaries and avoid cumulative timestamp drift in VAC/VAD chunk processing
- **CUDA cache cleanup** : Keep per-step decoder cleanup lightweight; CUDA cache release stays on coarse segment boundaries