product management

Author: lucidrains

README.md

@@ -149,9 +149,10 @@ trainer.train()
 
 - [x] complete perceiver then cross attention conditioning on ddpm side
 - [x] add classifier free guidance, even if not in paper
+- [x] complete duration / pitch prediction during training - thanks to Manmay
 
+- [ ] also offer direct summation conditioning using spear-tts text-to-semantic module, if available
 - [ ] add self-conditioning on ddpm side
-- [ ] complete duration / pitch prediction during training
 - [ ] take care of automatic slicing of audio for prompt, being aware of minimal audio segment as allowed by the codec model
 - [ ] make sure curtail_from_left works for encodec, figure out what they are doing