Closed michael-conrad closed 2 years ago
Shouldn't a smaller hop_sample length result in more samples and not less when dividing a sample up by hop_sample length?
The hop size is implicitly hard coded in the SpectrogramUpsampler
(in model.py
): this logic is responsible for upsampling the input spectrograms to the same rate as the output audio. The two ConvTranspose2d operations upsample the rate by a factor of 256 (16 x 16); you can play around with the stride and padding of these transposed convolutions to target different hop sizes.
You'll also want to re-run preprocess.py
if you change the hop size.
I don't where at in the code, but there is effectively a hard coded requirement of 256 for hop_samples length:
Errors for different hop_samples != 256:
where tensor_a size = 50*hop_samples and tensor_b size = 50*256