so-vits-svc fork with realtime support, improved interface and more features.
Google collab for testing SoftVC VITS Singing Voice Conversion for AI capable of changing the singer within music files.
Score-to-ContentVec: a model that gives ContentVec-based SVC voice models (so-vits-svc, RVC) the ability to sing from a score (MIDI notes + lyrics).
Patches to train RVC v2 voice models for free on modern Google Colab (Python 3.12 / numpy 2.x / torch 2.x). Removes fairseq, fixes PyAV+matplotlib breakage.
realtime support, improved interface and more features.
Convert MIDI notes and lyrics into ContentVec features to enable singing from a score using existing SVC or RVC voice models.
Add a description, image, and links to the contentvec topic page so that developers can more easily learn about it.
To associate your repository with the contentvec topic, visit your repo's landing page and select "manage topics."