sp-uhh / sgmse

Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
MIT License
454 stars 69 forks source link

Try to run on CPU #28

Closed SediRzm closed 2 months ago

SediRzm commented 1 year ago

Hi, I have tried to run the model (just run) using CPU, instead of Cuda. I have changed all places the .cuda to .cpu and set the device to cpu as well. I face the IndexError: list index out of range. Do you have any suggestion? I have run it before on GPU on another system. I need to change to CPU now. Do you have any solution?

julius-richter commented 2 months ago

I the latest commit, I have added the argument --device to enhancement.py. You can now run the enhancement on CPU with --device cpu.