Description

( An updated model with a better dataset, more training and stuff then my last B1 model. imo it sounds a lot better. This was made with multiple sources, the films, games, etc. Can be used for talking or singing. Respective epochs in the zip file. Trained with 2h 30m of audio (Probably more but I am too lazy to check lmao). If you use this model in a song or smth and post it then please credit the model. ty! :3