NVIDIA/mellotron

Inference failed

lqniunjunlper opened this issue · 1 comments

When use mellotron.inference(), these is a "Warning! Reached max decoder steps";
While user inference_noattention(), final audio is confused!

Train loss 6010 0.283912 Grad Norm 0.313008 2.66s/it

BTW, what is the most important input feature for mellotron to produce a good performance?

Please share alignment maps, training and validation losses, and samples.