Raafi
You can achieve it using the following code, considering you have already transcribed it. `model_a, metadata = whisperx.load_align_model(language_code=result["language"], device=device) result = whisperx.align(result["segments"], model_a, metadata, audio, device)`
import logging import nltk # Set nltk logging to ERROR only to suppress information messages logging.getLogger("nltk").setLevel(logging.ERROR) try this
Is anyone assigned/working on it?, if not I can give it a try. Sounds interesting to me.
Hello all, let me know further steps! @Evanev7 @AlexCheema
> Good catch, but definitely an upstream issue for us - have you reported this to MLX as well? Nope, not yet, will do. Below is the log ss.
## Summary of Changes **1. Error Handling** - Removed try/except block in vision model generation - exceptions now propagate to caller **2. Type Safety** - Added `Union[TextTokenizer, VisionProcessor]` type hints...