Happy (belated) new year!
— Nao Tokui (@naotokui_en) January 3, 2022
I had plenty of time, OP-1, headphones, and a great working environment at my parents' house during the break. So I decided to make a track using the RAVE neural synthesis model trained on speech data with the real-time plugin!! ๐๐ง pic.twitter.com/hRYLJM9oRU
This is uber-cool! Kudos to Andrew Fyfe, Bogdan Teleaga @bteleaga_ and @antoine_caillon !!
— Nao Tokui (@naotokui_en) December 21, 2021
Realtime Voice to Darbuka transfer https://t.co/8HHZaXfVwC pic.twitter.com/0kofj2XAyO
Some grindcore music generated with RAVE accompanied by #StyleGAN3 audio reactive video trained on Thanka painting images pic.twitter.com/tfnuPeNCXP
— Diwas Bhattarai (@di_was) December 30, 2021
๐ค pic.twitter.com/6afqounxhE
— Diwas Bhattarai (@di_was) January 10, 2022