wnhsu / scalablefhvae Goto Github PK

Does FHVAE have the code of PyTorch or tensorflow-gpu 2.X ?

Hi. Thank you for sharing this code. And I have a question.
Why use state.h rather than out to be the output of the encoder for FHVAE with lstm?

hello, the code just make one sequence as a class. How can I use the variables "lab_specs" to solve it?

Thanks for open sourcing the code!

I am trying to synthesise some transformed audio from log mag spectrograms. How did you do it? Did you use any particular Griffin lim implementation?

Hi
I was wondering if it could be possible for you to make available any pretrained model for the given code. I am interested in using the feature space of Scalable FHVAE for an audio based task of mine.

Thanks