galgreshler

Hello, we have tried several more types of audio types in bandwidth extension, such as saxophone, trumpet, etc., but we haven't conducted extensive analysis as we did for speech. Nevertheless,...

Hi, The code wasn't meant to be installed as a package, so I guess that's why you get that error. I will try to add in the future a notebook...

Hi, I haven't implemented such a feature, but it should be quite easy: since training is done for each scale independently, and for each finished scale the networks are saved,...

Yes, but this is already done during training. If you want to implement continuation of existing model, you have to load its saved networks and continue training of the following...