Did you ever tried to evaluate your model?

rishikksh20 / hifigan-denoiser

HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

Apache License 2.0

208 stars 45 forks source link

Did you ever tried to evaluate your model? #10

Open duanwwww opened 1 year ago

duanwwww commented 1 year ago

I wonder whether tried to test the score for all the checkpoints you trained. Your model juest output the same waveshape you input .Your model can output the input waveshape even you don't train the model. What's more, if anyone who want to find the code for paper Hifi-GAN and you fortunately see this issue, please go to the correct repository: https://github.com/jik876/hifi-gan

coreeey commented 1 year ago

Have you ever trained this network? When I tried to train this network, I found that after adding a postnet, the performance of the main generator network deteriorated. Therefore, is it necessary to freeze the generator during the training of the postnet?