It would appear that there is a file missing from the original openai model design → preprocessor_config.json
When loading the model:
.venv/lib/python3.12/site-packages/mlx_audio/stt/models/whisper/whisper.py:695: UserWarning: Could not load WhisperProcessor: Can't load feature extractor for '.cache/huggingface/hub/models--mlx-community--whisper-large-v3-turbo/snapshots/beea265c324f07ba1e347f3c8a97aec454056a86'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure '.cache/huggingface/hub/models--mlx-community--whisper-large-v3-turbo/snapshots/beea265c324f07ba1e347f3c8a97aec454056a86' is the correct path to a directory containing a preprocessor_config.json file.
warnings.warn(f"Could not load WhisperProcessor: {e}.")
I can go around it anyway, it is a warning but it would appear that the it is looking for a preprocessor_config.json (latest version of mlx_audio: 0.3.1)
The original model has all of the pieces: https://huggingface.co/openai/whisper-large-v3-turbo/tree/main
I will update it. 👌🏽