Closed crlandsc closed 9 months ago
@crlandsc hey Christopher! this looks great! thank you for addressing the multiple stem situation for mel-band roformer; overlooked it
No problem, thanks for reviewing so quickly and for this paper implementation! It's fantastic!
Are all of the default args for the mel-roformer based on the paper? Because I was having trouble replicating the exact number of parameters that they detail.
thanks for the kind words!
there could be tiny differences, but i think all the main points of the paper are already in there (axial attention, rotary relative positions, and overlapping frequencies bands for mel-band roformer variant)
by default i am using the librosa mel bank as they detailed in the paper
Ok, that is pretty much what I thought. I was also making sure that I wasn't messing something up on my end as I started to train with it. Thanks again!
thanks for the PR!
Changes:
torch.istft
function.dims
calculation to alignmask_estimator_depth
and MLPdepth
to be equal to the number of MLP hidden layers.mask_estimator_depth=2
attribute seemed misleading when it resulted in an MLP depth of 3 layers (1 in, 1 hidden, 1 out). The default value for the MLPdepth
was 1 andmask_estimator_depth
was 2. Now these are aligned to both be 1 and the attribute directly corresponds to the number of hidden layers in the MLPs.