Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Is it possible to train KSS dataset in master branch? #27

Open
taewhankim opened this issue Jul 20, 2021 · 2 comments
Open

Is it possible to train KSS dataset in master branch? #27

taewhankim opened this issue Jul 20, 2021 · 2 comments

Comments

@taewhankim
Copy link

taewhankim commented Jul 20, 2021

Thanks for sharing great result.
I want to train kss data for training vocoder to use in fastspeech2 with master branch code, is it possible?

Avg : g 1.3729 d 0.0000 ad 0.0000| step 5976: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 166/166 [05:01<00:00,  1.81s/it]
Avg : g 1.3659 d 0.0000 ad 0.0000| step 6142: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 166/166 [05:01<00:00,  1.82s/it]
Avg : g 1.3601 d 0.0000 ad 0.0000| step 6308: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 166/166 [05:06<00:00,  1.85s/it]
Avg : g 1.3537 d 0.0000 ad 0.0000| step 6474: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 166/166 [05:02<00:00,  1.82s/it]
Avg : g 1.3493 d 0.0000 ad 0.0000| step 6640: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 166/166 [05:05<00:00,  1.84s/it]
g 2.5462 d 3.1285 ad 1.0426| step 6640: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2196/2196 [00:46<00:00, 47.20it/s]
Avg : g 1.3415 d 0.0000 ad 0.0000| step 6680:  24%|██████████████████████████▌                                                                                   | 40/166 [01:14<01:10,  1.79it/s

Because d Loss and ad Loss didn't show any result, When I trained.

@Jackson-Kang
Copy link
Contributor

Jackson-Kang commented Jul 25, 2021

Hi, @taewhankim .

In this implementation, discriminator starts to train at 100,000 steps.
Before 100,000 steps, "d" (discriminator loss) and "ad" (adversarial loss) are printed as zero.

Also, I downsampled sampling rate of the KSS dataset to 22,050Hz.

@taewhankim
Copy link
Author

Thanks to reply! Have a nice day

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants