Experimental model
Added 2022-12-13 03:18:20 +0000 UTCThis is an experimental model for those curious about some of the testing I have been up to. Progress is not always linear and often times you have to try new and different things to get where you want. This is absolutely not a final model or even one I consider worthy of an update, but it has some neat features.
It handles pitch much better and even allows for singing. Additionally, some of the 'wobbliness' has been reduced. However for this model, it comes at the sizable cost of adding some amount of buzzing/robotic sound to it for certain voices and phonemes, so if you test it out keep that in mind!
If you want to try it out, download the zip file from the link at the top of this post. No installer as this is just for testing.
Progress is being made and my end goal is to get the model I have demonstrated in the Discord to work for live. Once that is working I plan on getting the user-submitted voice pipeline going.
Thank you all for your support which allows me to keep working on this!
