Results
1
comments of
Jack
I'm getting this too - I tracked it down to the following in mel_processing.py ``` spec = torch.stft( y, n_fft, hop_length=hop_size, win_length=win_size, window=hann_window[wnsize_dtype_device], center=center, pad_mode="reflect", normalized=False, onesided=True, return_complex=False, ) ```...