0.2.18

puckeditor/puck0.2.18Feb 13, 2026by QuentinFuxa

AI Summary

Addresses critical memory leaks in streaming mode and fixes several bugs related to translation flags, cache directories, and ASR token handling.

Key Highlights

Fixed VRAM leak in SimulStreaming decoding loop (capped to rolling window)
Fixed `--direct-english-translation` flag propagation to LocalAgreement backends
Fixed `model_cache_dir` being ignored in SimulStreaming
Added probability field to ASRToken for FasterWhisperASR

New Features

Added probability field to ASRToken
Added insert_audio_chunk method to DiartDiarization

Full Release Notes

## Bug Fixes

- **Fix SimulStreaming VRAM leak** :  cross-attention tensors were accumulating unboundedly during the decoding loop (up to env 5GB on repetition loops). Now capped to a rolling window (#283, #275)
- **Fix `--direct-english-translation` not working with LocalAgreement backends** : `task="translate"` was never propagated to the ASR backend's `transcribe_kargs`, so whisper always ran in transcribe mode regardless of the flag. (#306)
- **Fix `model_cache_dir` ignored in SimulStreaming** : download path was hardcoded to `None`. Also fixed `task` being passed as a boolean instead of a string (`"translate"`/`"transcribe"`). (#310)
- **Fix `NoneType` concatenation in `add_translation`** : crash when `ts.text` was `None` during translation overlay. (#296)
- **Fix `Segment().from_tokens()` bad classmethod call** : was incorrectly called on an instance instead of the class. (#331)
- **Fix `token.has_ended` type narrowing** : replaced `token.is_silence()` (non-existent method) with proper `isinstance(token, Silence)` check. (#329)

## Improvements

- **Add `probability` field to `ASRToken`** FasterWhisperASR now passes word-level probabilities through (#330, #313)
- **Add `insert_audio_chunk` to `DiartDiarization`**, brings the interface in line with `SortformerDiarization` (#332)
- **Initialize `OpenaiApiASR.task`** : was previously referenced but never set, causing potential `AttributeError`.