rishikksh20 / HiFiplusplus-pytorch

HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Single frequency lines in Spectrogram of generated wavs

williamsz opened this issue · comments

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 , as shown in the figure
截屏2022-11-01 18 56 34