This is Version 2 of the Clyde model.
Added an extra minute in the dataset, hopefully making this version a little better. Still has a slight ringing effect, but it's weaker now (Still noticeable, but hardly).
(Recommended for singing, but optional for speaking.)
-
Credit: "Randomly Created AI" on YouTube (Not required, but would be appreciated).
-
Link to V1: https://discordapp.com/channels/1159260121998827560/1227408173195984926/1227408173195984926
-
Link to V3: https://discordapp.com/channels/1159260121998827560/1237055371357585438
https://huggingface.co/RandomlyCreatedAI/ClydeDonovanV2/resolve/main/ClydeDonovanV2.zip