Mikey Shulman: belief

Transcript context

…And what's the data recipe for turning a good music model? Like what percentage genre do you put, like also do you split vocals and instrumentals? So you have to do lots of things. And I think this is the biggest area where we have, you know, sort of our secret sauce. I think to a large extent, what we do is we benefit from all of the beautiful things people do with transformers and text. And we focus very hard basically on how do I tokenize audio in the right way. And without divulging too much secret sauce, it's at least similar to how it's done in sort of the open source stuff. You will have different models that learn to encode audio in discrete representations. And a lot of this boils down to figuring out the right, let's say, implicit biases to put in those models, the right data to inject. How do I make sure that I can produce kind of all audio arbitrarily? That's speech, that's background music, that's vocals, that's kind of everything to make sure that I can really capture all the behavior that I want to. Yeah, that makes sense. And then in terms of some of... We had our monthly recap last month, and the data wars were kind of one of the hot topics. You saw the New York Times lawsuit against OpenAI, because you have obviously large language models in production. You don't have large music models in production. So I think there's maybe been less of a trade there, so to speak. How do you kind of think about that? There's obviously a lot of copyright-free, royalty-free music out there. Is there any kind of power law in terms of like, hey, the best music is actually much better to train on, or in music does it not really matter because the structure of some of the musical structure is kind of the same?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.