v0.2.22

semaphoreui/semaphorev0.2.22Jun 4, 2026by QuentinFuxa

AI Summary

This release focuses on audio processing improvements including language alias normalization for Whisper Chinese codes, VAD event handling enhancements, and CUDA cache optimization for decoder performance.

Key Highlights

  • NLLW language aliases normalization (zh -> zh-CN)
  • VAD event handling to preserve silence boundaries
  • CUDA cache cleanup for lightweight per-step decoder operations
  • Prevention of timestamp drift in VAC/VAD chunk processing

New Features

  • Whisper Chinese language code normalization
  • Improved VAD/VAC audio processing
  • Optimized CUDA cache management

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