Spaces:

Xenova

/

whisper-speaker-diarization

like 230

Running

Hello!

This space is currently broken because of the requestAdapterInfo() webGPU function being deprecated: https://developer.mozilla.org/en-US/docs/Web/API/GPUAdapter/requestAdapterInfo

I fixed this by upgrading to the latest version of the @huggingface/transformers library. I also added some new features: Loading bars now show for decoding the audio file, (though it only does 0% and 100%), and for transcribing the audio file itself with progress, so the user can see visible progress as the transcription occurs.