Skip to content
Discussion options

You must be logged in to vote

In "transcribe" mode, the source and target language are the same.
In "translate" mode it's as I said, the target language can't be set, it's always english.

For example, if you have the source audio in spanish and want the resulting text to be in german, you would use "transcribe" to get the spanish transcript. You will then have to implement the spanish-to-german translation yourself, as a separate step (using opus-mt, madlad400, whatever).
(Or alternatively, if you use "translate" mode you will get the english text and you will then have to translate that to german yourself. But the timing information might suffer in this case.)
Getting the timing right for the translated version might…

Replies: 1 comment 5 replies

Comment options

You must be logged in to vote
5 replies
@thejame
Comment options

@misutoneko
Comment options

@thejame
Comment options

@misutoneko
Comment options

Answer selected by thejame
@thejame
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
2 participants