LEE CHOONGHO

Thanks for your help. I'll try it!

> > Thanks for your help. I'll try it! > > I reach the same. > > Is there any problem when I keep training with that problem: "No module...

@OnceJune Thanks for your Reply. fastspeech2 duration predictor works well. Audio sample synthesized by ddp is like below. https://user-images.githubusercontent.com/44384060/154802366-3e1a959f-8652-4adb-95f8-f234ceb09d87.mp4 I think that's a very good point. However, as mentioned in...

@nzpeng flow module with two kl_losses is bidirectional prior/posterior module proposed in Naturalspeech[1]. And in my experience, It seems to be superior to original vits`s flow module in terms of...

@patriotyk Sorry, I've change the code to log on WandB server. I have no local logging files nor tensorboard logs.

> > Training Loss, Generated Outputs. > > I hope this will be a reference for model training. > > https://api.wandb.ai/links/xi-speech-team/k0kdfwch > > TKS for your work,could your share 32k...

> Do you have a standard tensorboard logs? It is interesting to compare. > What is your validation loss on the last checkpoint? It is encoded in to the checkpoint...

And I think delta should be less than 1.0. Even lower than d scale. In the reference paper of nansy++, delta is 0.25 * d_scale(sigma in the paper). https://arxiv.org/pdf/1910.11664.pdf

Thank you for your reply @revsic . I also have a question. In the paper, F0 is calculated by weighted sum of 64 bins of pitch encoder's output. which requires...

Hello, @talipturkmen @pranavmalikk . I'm sorry for the late response. The training of the pitch estimation system claimed in the Paper did not work by any means. (In my case)...