Starstruk Logo MarkStarstruk

v0.2.22

SimonGiebenhain/MonoNPHMv0.2.22Jun 4, 2026by QuentinFuxa

AI Summary

This release focuses on core audio processing stability, normalizing Chinese language codes for transcription and fixing timestamp drift in Voice Activity Detection (VAD). It also introduces lightweight CUDA cache management to improve performance.

Key Highlights

  • NLLW language alias normalization for Whisper Chinese codes
  • Improved VAD event handling to preserve silence boundaries
  • CUDA cache cleanup for lightweight decoder management

New Features

  • NLLW Chinese language code normalization (zh -> zh-CN)
  • VAD silence boundary preservation
  • Lightweight CUDA cache release on coarse segment boundaries

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