Closed dorpxam closed 10 months ago
@dorpxam hey, so target
and raw_audio
are actually two different inputs
target
is the expected output for each of stems
and yea, we can refine the hyperparameters a bit more, let me get that done
@ZFTurbo the stem feature is working for your kaggle stuff?
@lucidrains Oh, I look so dumb now. I hope you understand that my issues are not to criticize or call into question your work. I'm autodidact and learn step by step, so I often say rubbish bigger than me.
That the model is capable of generating the mask of a target from a source and based on a loss function, that makes sense. But generating multiple masks only based on a loss function without the targets being involved in the model is black magic for me :)
Hi @lucidrains
I'm working on a training code to share here and attempt to reproduce the same workflow than the SAMI-ByteDance paper. I will share the code here. In order to make the training code generic, and because I'm pretty newbie in this kind of task, I want to be sure to clearly understand your code.
Num_Stems parameter
EDIT: I remove this very stupid assumption.
Divergence of default parameters
This is a less important, but for better following of the code:
I don't know if the choice of
attn_dropout = 0.
andff_dropout = 0.
as default parameters for theTransformers
is motivated by some technical considerations. If not, maybe it's better to change the values to follow the original paper?Same here with the default parameter
num_bands = 62
of theMelBandRoformer
?