benchrus

Results 5 comments of benchrus

Is this project available on Windows 10

Thanks for the answer, I have NVIDIA A40, installed torch=2.0.0, cuda 11.7. I'll check. Thanks again.

fine-tuning does not seem to improve/converge

Hi, I have finetuned whisper-small model and I really want to know how to transcribe an audio file with finetuned model. Please Help me...

pytorch_model.bin not getting saved

Sorry, I got the same issue. I followed your advice, changed the warmup steps lower than num_epochs, but it's not fixing this issue. Please help me.

IndexError: index 676 is out of bounds for dimension 0 with size 676

Hi, I have the same problem. Always IndexError appears and same error with different lengths of drive audio. How can I solve this problem?

The result video will flicker when human's eyes close.

23s length may not enough yes, but before this, I trained with 6s video and got good result. And what I want to know is that the training material **MUST**...