TITAN is a state-of-the-art pretrained model designed for RVC training. It offers a robust solution for transforming voice characteristics from one speaker to another, providing high-quality results with minimal training effort.
Model Details
Titan-Medium
- Iterations (48k): 1018660 Steps and 530 Epochs
- Iterations (40k): 1010588 Steps and 467 Epochs
- Iterations (32k): 1001469 Steps and 463 Epochs
- Fine-tuning Process: RVC v2 pretrained with pitch guidance, Rmvpe, leveraging an 11.15-hour dataset sourced from Expresso (https://arxiv.org/abs/2308.05725) also available on https://huggingface.co/datasets/blaise-tk/TITAN-Medium.
Collaborators
We appreciate the contributions of our collaborators who have helped in the development and refinement of TITAN.
- Mustar
- SimplCup
- UnitedShoes
Beta Testers
We extend our gratitude to the beta testers who provided valuable feedback during the testing phase of TITAN.
- SimplCup
- Leo_Frixi
- Light
- SCRFilms
- Ryanz
- Litsa_the_dancer
Download
- 48k: Pretrained G.pth & D.pth | Model .pth & .index
- 40k: Pretrained G.pth & D.pth | Model .pth & .index
- 32k: Pretrained G.pth & D.pth | Model .pth & .index
TITAN is currently the best general-purpose pretrained for RVC. I strongly recommend future pretrained creators to start their finetuning from TITAN!