mirror of
https://github.com/QuentinFuxa/WhisperLiveKit.git
synced 2026-03-07 14:23:18 +00:00
8c799fa4d1
fixes #283, fixes #275 - accumulated_cross_attns was growing unboundedly during decoding loop, using up to ~5GB for repetition loops. now capped to rolling window of 16 - max_tokens_per_chunk was using TOKENS_PER_SECOND (mel frame rate = 50) instead of actual text token rate (~15/s), allowing 10-40x too many decoding steps - removed unused torch.cat on early return path - removed dead self.committed/last_result_tokens lists (never read) - same fixes applied to mlx variant