Description

This model was trained using RVC v2 (RVMPE 300 Epochs) after building the dataset with Eric Lapointe best selling albums (FLAC Lossless) quality. Each tracks were isolated (Vocals/Instrumental) using UVR5 (BS Reformer ViperX 1297/1296 & MDXC23 Karafan Ensemble method). Note that not every tracks were used for the dataset creation because of artifacts and back vocals that were too much present. Even models like HP2-Karokee and BVE model will almost always leave some residue that you don't want to have in your dataset. For additional details for you nerds like me out there each and every vocals were individually isolated and cleaned (De-Reverbed with UVR-DeReverb-DeEcho, then De-Noised manually with iZotope RX 10 Spectral Denoiser & Supertone 'GOYO' Voice Separator). Model trained using RVC v2 and new optimized Pretrained models 'D-F040k-TITAN-Medium.pth' and 'G-F040k-TITAN-Medium.pth', RVMPE, 300 Epochs. The initial Epochs amount was 350 but there was some overtraining at 300 Epochs, which is where I stopped and created this model/index (Thanks to TensorFlow).