Align load_models.py to latest MLX version for quantization

mustafaaljadery / lightning-whisper-mlx

An extremely fast implementation of whisper optimized for Apple Silicon using MLX.

469 stars 21 forks source link

Closed ivanfioravanti closed 2 months ago

ivanfioravanti commented 2 months ago

This to fix Issue #11

kadirnar commented 1 month ago

I updated the code but it doesn't work. Can you fix this?

ValueError: [addmm] Last dimension of first input with shape (1,1500,1280) must match second to last dimension of second input with shape (160,1280).

x4080 commented 2 weeks ago

@kadirnar I got the same result, did you find the solution ?