James

Thanks for good paper and project. My experiment is similar to Buckingham's. The validation loss fluctuates around 100 after 30K iterations without further improvement. I haven't figured out what is...

@auspicious3000 Yes. Thank you for pointing this out. After starting to use full P226 and P231 in VCTK corpus. The training and validation charts look reasonable now, but the reconstruction...

@auspicious3000 Thanks for your suggestion, I have trained the 80 speakers(P225~P304) in VCTK dataset(due to onehot size is 80) on 2080Ti GPU for 2 days, the result becomes better, but...

I believe the implementation is right, but the paper definition is likely not correct(max instead of min or adding -). May someone confirm it? Thanks.

Ditto, but using randint may cause irreproducible.

Same here