ermatter.blogg.se - Stellarium desktop

Instructions can be found below under Inference GUI 2 header.

Inference GUI 2 features experimental TalkNet integration, in-program recording, as well as other features like timestretching with rubberband.

There is one gui using PySide6 inference_gui.py and one gui using PyQt5 currently a work in progress inference_gui2.py.

Some modifications have also been made to pitch inference for better performance.This fork has some modifications to make it work better on Windows and with smaller multi-speaker datasets.Additionally, changing the vocoder to NSF HiFiGAN to fix the issue with unwanted staccato.

SoftVC VITS Singing Voice Conversion Model OverviewĪ singing voice coversion (SVC) model, using the SoftVC encoder to extract features from the input audio, sent into VITS along with the F0 to replace the original input to acheive a voice conversion effect.