yanggeng1995 / eats Goto Github PK

View Code? Open in Web Editor NEW

126.0 126.0 18.0 837 KB

A pytroch implementation of the EETS: End-to-End Adversarial Text-to-Speech

Python 100.00%

eats's People

Contributors

Stargazers

Watchers

Forkers

entn-at wgwangang dedkoster martincastellano tsaifangsheng renyuanl blgnksy vingovan liujingxiu23 huukim136 sciai-ai saber5433 maxmax2016 andymyzhang32 ajitkumar15 batikim09 66mhz amorjnyh zhongshijun

eats's Issues

will you release any samples?

great work and hope there're some samples that could be shared

Your Aligner should eliminate For loop to let model training faster :D

Where's the DTW loss?

Hi,

Thanks for making the implementation available for this research paper...Can you point me to the place you compute the DTW loss? I see that there's Multi resolution STFT loss...

EATS/utils/loss.py

Line 77 in 1e7c73d

class MultiResolutionSTFTLoss(nn.Module):

--> i have a hard time understanding if this has the DTW component to the loss.

Missing Generator Under Models and names.pkl

Generator module is missing
if possible could you please shre the dataset and folder sctucture as names.pkl file is missing.

Can you please help

Missing Generator Under Models

Traceback (most recent call last):
  File "train.py", line 12, in <module>
    from models.generator import Generator
ModuleNotFoundError: No module named 'models.generator'

Recommend Projects