Kaizhi Qian

Sure. I can send the dockerfile to your gmail.

@lyriccoder I installed most things manually after starting the docker. Unfortunately, those steps are not reflected in the dockerfile.

@lyriccoder Unfortunately, it's been a long time, thus I don't have the commands anymore. The dockerfile is just a simple base image.

What does your input and output spectrogram look like?

decoder and encoder are different, they don't share weights

yes, just feed the reconstruction back into the encoder

The training code for P is almost identical to solver.py. You can get it by modifying solver.py based on the description in the paper.

For different dataset you need to retune the bottleneck. Also, feel free to try different encoder and decoder architectures. The paper proposed a framework instead of specific architectures. Voxceleb2 is...

Good question. AutoVC can disentangle accent to some extent but not sufficient. Disentangling accent is another interesting research problem. We do not have a solution for that.

Accent may be a part of each component.