HiFiplusplus-pytorch

HiFiplusplus-pytorch copied to clipboard

mel_error is Nan

1

 mel_error is nan in the first step when training by config_v2.json, is there anyone who meets the same problem? And how to fix it?

fengshi-cherish

 I trid modifying code a bit but the issue is still the same. Can you help?

CodeWith-Addy

Hi, I traned a model for the Bandwidth expansion task using the code and VCTK dataset. But I got bad generated wavs, which contain Single frequency lines in Spectrogram ,...

williamsz

which is better for TTS, hifigan vs hifi++?

2

which is better for TTS, hifigan vs hifi++?

Liujingxiu23