faran
faran
Thanks so much. Is this how you trained the new upcoming model?
I make suggested change and get artifcat like reported here: https://colab.research.google.com/gist/tulasiram58827/8a7660ab21ca3ea246141bbe4b0f87c0/hifigan_issue.ipynb
OK, Thanks. You use it to load PNG / JPEG images that you first read into a C++ array?
Thanks! You generate the spectrograms offline using Python (npy) and then read them from C++?
Library looks amazing. Does it only work as a plug-in?
And you use U-net for process spectograms?
Yes, I register on steinberg but no can download. Will try again later.
Thanks! How did you read a wav file into a torch::tensor? Using any third party? Thanks.