mirror of
https://github.com/ggml-org/whisper.cpp.git
synced 2026-08-04 09:00:54 -05:00
- The encode/decode memory buffers are now reused - If the 30-sec segment goes for too long without a timestamp token, we force one. Improves transcription for large model - Stereo support - Add "micro-machines.wav" sample
84 KiB
84 KiB