[andrew-w]

All for suggestions! We've tried white noise as well, but it only works on plain talking samples (not music, for example). My guess is that the most robust solution will come from updating how it's trained.

[bobbylarrybobby]

What if you train it to hold the last frame on silence (or quiet noise)?

[andrew-w]

We've talked about doing something like that. Feels like it should work in theory.

[jazzyjackson]

Or noise corresponding with a closed mouth

Hmmmmmmmm

Ohmmmmmmm