I see that there's no SRV model and i want to use it with my voice to make a song from Tom and Jerry that sounds like blues,and sadly i don't have a good CPU and now the things in Colab are worse so i can't do it in local.
If someone can help me to create it,i'll be so glad about it,i can help giving a dataset thanks to Rock Band's Texas Flood DLC album to make minus work...you can send me DM to talk more about it,thanks!