Re:Google SoundStorm: Efficient Parallel Audio Generation
by og_kalu on Sunday July 16, 2023 @01:48PM
(#36749698)
The creators won't say as far as i know but bark looks to be trained on lot of youtube corpora (rather than typical ML audio datasets) where audio may have transcripts like that and why stuff like [laughs] work
[ Parent
| on HN ]
Re:Google SoundStorm: Efficient Parallel Audio Generation
by JonathanFly on Sunday July 16, 2023 @02:18PM
(#36749985)
Yeah I often try to think about what might be in a YouTube caption when finding prompts that work in Bark. But pipe character isn't one I remember seeing on YouTube. Maybe it's part of some other audio dataset though. Or maybe it's on YouTube but only in non English videos.
Re:Google SoundStorm: Efficient Parallel Audio Generation
by neilv on Sunday July 16, 2023 @04:16PM
(#36751008)
In the future, will children think it's normal to talk like, "Hey, what up, Youtube! ... Be sure to like and subscribe! ... Smash that like button! ... Let me know in the comments down below!"?
I wonder how ML trained on the tone transitions to a sponsored segment dripping with secret shame... would infect general speech.
