v0.2.24
MagicMirrorOrg/MagicMirrorv0.2.24Jul 11, 2026by QuentinFuxa
AI Summary
This release introduces streaming LLM translation via the AlignAtt backend, refreshes benchmark measurements on an H100, and improves error handling for ASR backends.
Key Highlights
- Streaming LLM translation using AlignAtt4LLM backend
- Benchmark figures re-measured on an H100
- Fixed mlx-whisper producing empty captions with torch >= 2.13
- Added loud failure handling and watchdog for ASR backends
New Features
- AlignAtt translation backend support
- Updated benchmarks for current backends
- Enhanced error logging and watchdog for ASR failures
Full Release Notes
Streaming LLM translation, refreshed benchmarks and loud failures. ## Added - AlignAtt translation backend (`--translation-backend alignatt`): streaming LLM translation through an [Alignatt4LLM](https://github.com/QuentinFuxa/Alignatt4LLM) sidecar. The model drafts ahead over the unstable ASR tail and commits only target words whose attention lands on committed source words, so translations are append-only and released the instant the ASR commits. See [docs/translation-alignatt.md](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/docs/translation-alignatt.md). - Benchmark figures re-measured on an H100 with the current backends (the README scatter plots dated from March and misrepresented the qwen3 backends). Raw results in `benchmarks/h100_scatter/`. ## Fixed - mlx-whisper produced empty captions with torch >= 2.13 (#383, thanks @RobertBartelds-FleetEnergies). - The server now fails loudly when the ASR backend produces nothing: warmup errors abort startup with the cause, and a watchdog logs an explicit error if audio flows but no text is ever produced.