Files
FunASR/funasr/utils
游雁 80f3f2a4e9 fix: SenseVoice+spk_model crash and torchaudio>=2.11 compatibility
1. auto_model.py: When ASR model (e.g. SenseVoice) doesn't produce
   timestamps, automatically fall back to vad_segment mode for speaker
   diarization instead of crashing. Fixes #2945.

2. load_utils.py: Add soundfile as fallback when torchaudio.load fails
   (torchaudio>=2.11 requires torchcodec). Falls through to ffmpeg only
   if soundfile also fails.
2026-05-30 02:27:59 +08:00
..
2022-11-26 21:56:51 +08:00