Open skol101 opened 2 years ago
There are so many ways...
First, check a preprocessing method for your Mel-spectrogram Second, change the initial frequency value for resampling
https://github.com/sh-lee-prml/BigVGAN/blob/main/models_bigvgan.py#L104
Calculate this according to your sampling, hop size, and upsampling rate
I'll show you an example when using hop size of 256 and upsampling rates =[8,8,2,2])
16000 sr --> initial_freq = [500, 4000, 8000, 16000] 22050sr --> initial_freq = [690, 5513, 11025, 22050] 24000sr --> initial_freq = [750, 6000, 12000, 24000]
Cheers, I'll test it out.
For different sampling rates, do you need to modify the parameters of MPD, similar to https://github.com/jik876/hifi-gan/issues/58.
Would be nice if you provided clear instructions on how this model can be trained on different sampling rates.