Hi everybody,

has anybody successfully run Retrieval-based-Voice-Conversion on an aarch64 system, for example nVidia Jetson AGX Orin?

praat-parselmouth does not natively work. I got it installed manually, but the project does still not work. It does not recognize any GPU, so training is not possible.

I can provide logs and/or try a fresh install, just let me know what output you need, and, in case there is another method other than venv, how I should install packages and I'll post everything here.

Thank you in advance for your help :)