Current code doesn't work with hifigan about styletts2 HOT 4 CLOSED

I think it works. The finetuning code uses hifigan as decoder and everyone could run it. Are you training from scratch and using wrong upsample rates?

from styletts2.

I think it works. The finetuning code uses hifigan as decoder and everyone could run it. Are you training from scratch and using wrong upsample rates?

The error occured I'm training stage 1 from scratch. I didn't change upsample rates. When the vocoder is not hifigan, whether it's stage 1 or stage 2 or finetune, it works fine.

from styletts2.

@zhouyong64 The LibriTTS model is HifiGAN, how come it doesn't work if you could finetune it? I think you need to change the hyperparameters to make it suit HifiGAN like using this configuration instead: https://github.com/yl4579/StyleTTS2/blob/main/Configs/config_libritts.yml

What's the error you got for using hifigan as a decoder?

from styletts2.

@zhouyong64 The LibriTTS model is HifiGAN, how come it doesn't work if you could finetune it? I think you need to change the hyperparameters to make it suit HifiGAN like using this configuration instead: https://github.com/yl4579/StyleTTS2/blob/main/Configs/config_libritts.yml

What's the error you got for using hifigan as a decoder?

I'm training on Chinese data. Now I see I used the wrong configurations. Thanks for help.

from styletts2.