lianabagh

Do you use this same subband decomposition for voicefixer discriminators?

Is there any explanation why you didn't implement this part in C++, and instead did it in Python using torch.autograph.Function? @staticmethod def backward(ctx, deltas): ...... lngrads = lngrads * expLNs.reciprocal()...

The current implementation of the ConcatDataset class in the provided codebase enforces a requirement that all datasets within the ConcatDataset must have the same length for the __getitem__ function to...

Hi, I am currently exploring the model. However, I am seeking more information about the training dataset used for this model to better understand its context and applicability for my...

When I want to change the segment size to 130. It gives me an error. RuntimeError: shape mismatch: value tensor of shape [2048, 4096] cannot be broadcast to indexing result...

Hi, Great work and great results!! Does a combined model handle bandwidth extension, denoising and dereverberation ? Or seperate models for each task ?