v0.2.24

QuentinFuxa/WhisperLiveKitv0.2.24Jul 11, 2026by QuentinFuxa

AI Summary

Introduces the AlignAtt streaming LLM translation backend, refreshes benchmark figures on H100 hardware, and improves error handling for ASR backends that fail to produce output.

Key Highlights

New AlignAtt translation backend for streaming LLMs
Benchmark figures re-measured and corrected on an H100
Fix for mlx-whisper producing empty captions
Added loud failure warnings for ASR backends with no output

New Features

AlignAtt translation backend
Benchmark data refresh
Loud failure detection for ASR backends

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.