Open taewhankim opened 3 years ago
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.
Thanks to reply! Have a nice day
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?
Because d Loss and ad Loss didn't show any result, When I trained.