Octopus 3d51d63490 fix: suppress false-positive warnings when loading whisper audio encoder ... When a full whisper checkpoint (encoder + decoder) is loaded via AudioEncoderLoader, two classes of spurious warnings were emitted: 1. 'unexpected audio encoder' for every decoder.* key - the decoder is not part of WhisperLargeV3, so these keys are always present in full whisper checkpoints and should be silently discarded. 2. 'missing audio encoder' for feature_extractor.mel_spectrogram buffers (window and mel_scale.fb) - these are torchaudio buffers computed deterministically from config at init time; they are never stored in standard whisper checkpoints but are always correctly initialised. Fix: strip decoder keys from the state-dict before loading, and suppress warnings for the two known torchaudio-computed buffer keys. Fixes #13276		2026-04-04 13:45:54 +08:00
..
audio_encoders.py	fix: suppress false-positive warnings when loading whisper audio encoder	2026-04-04 13:45:54 +08:00
wav2vec2.py	Cleanup. (#9838)	2025-09-12 21:57:04 -04:00
whisper.py	Add encoder part of whisper large v3 as an audio encoder model. (#9894)	2025-09-16 01:19:50 -04:00