Skip to content
Discussion options

You must be logged in to vote

It could be a phenomenon similar to #204 and #194; could you try giving a prompt that might have come before the audio?

In general, it's an open research question to reliably control the model to prefer a certain format.

Replies: 4 comments 8 replies

Comment options

You must be logged in to vote
2 replies
@maugas
Comment options

@jongwook
Comment options

Comment options

You must be logged in to vote
1 reply
@maugas
Comment options

Answer selected by jongwook
Comment options

You must be logged in to vote
1 reply
@jianfch
Comment options

Comment options

You must be logged in to vote
4 replies
@sushant-samespace
Comment options

@itaipee
Comment options

@Sarathharidas
Comment options

@itaipee
Comment options

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
7 participants