search

argmaxinc / WhisperKit

On-device Speech Recognition for Apple Silicon
http://argmaxinc.com/blog/whisperkit
MIT License
3.92k stars 330 forks source link

Added MLX feature extractor implementation #129

Closed jkrukowski closed 6 months ago

jkrukowski commented 6 months ago

Based on https://github.com/ml-explore/mlx-examples/blob/c012eb173f0f632e369ec71f08be777df3aede08/whisper/whisper/audio.py#L130 implementation

I've compared the outcome of the python implementation (based on first 30 seconds of Alice.mp3): pyalice30

To this one: alice30