Dual-Path-RNN-Pytorch
Dual-Path-RNN-Pytorch copied to clipboard
Input Normalization
I'm not sure if my mixing is exactly same as yours, but does your torchaudio read the wav files to int(value is typically around a couple hundred) or to float values between [-1, 1]?
I started with scipy which loads to int, and it caused loss going to NaN at a point. So I switched to librosa which loads to float
float values between [-1, 1]. if you started with scipy which loads to int, you will norm audio between [-1,1]