Starstruk Logo MarkStarstruk

v0.2.22

parruda/swarmv0.2.22Jun 4, 2026by QuentinFuxa

AI Summary

Focuses on audio processing improvements including NLLW language aliasing, Voice Activity Detection (VAD) timestamp handling, and CUDA cache optimization.

Key Highlights

  • NLLW language code normalization (zh -> zh-CN)
  • VAD timestamp drift prevention in chunk processing
  • Lightweight CUDA cache cleanup strategy

New Features

  • NLLW language aliases
  • Improved VAD event handling
  • CUDA cache management 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