The new multi-genre model sounds awesome. But for some reason the new GUI that was just updated is much slower than the one from yesterday. If it takes me 20 seconds to process track with CMD and the first GUI, this one takes 5-6 minutes.
The new multi-genre model sounds awesome. But for some reason the new GUI that was just updated is much slower than the one from yesterday. If it takes me 20 seconds to process track with CMD and the first GUI, this one takes 5-6 minutes.
***UPDATE***
A compiled exe version for Windows is in the works for those who are having issues with the Python installs. I'm actually getting some help on it and hope to have it released by this weekend! I'm also going to add the option to save the png mask file that comes with each conversion, as well as the "post-process" option (that's a dev option, don't use it unless you know what you are doing!).
I also made a Google Colab version of it, for those who wanna use it there (mainly did it for a friend of mine who had issues on Mac).
It all works as intended, though the processing is slow due to not using a GPU. I just need to iron out some few issues and I will upload it here with instructions on how to install it (it's straightforward).
Last edited by djtayz; 05-06-2020 at 00:21.
Would it be possible to optimize it a little more by utilizing CPU and GPU to increase processing times on lower end systems?
Last edited by NewAgeRipper; 05-06-2020 at 23:58.
@Anjok Would it be possible to provide an update for the command line method. That would be better for me I think.
Last edited by NewAgeRipper; 05-06-2020 at 23:58.
I feel like something is missing. I followed the steps exactly and cannot get the GUI to open. Made sure all permissions were granted and I only get a command prompt that on first opening said something with an error but didn't stay open long enough to see what the error pertained to.