Skip to content
Discussion options

You must be logged in to vote

The model is not trained for that; it occasionally does it when you set task="translate" and language as the target language, but it's mostly due to imperfect language id in the training data, and it won't be very reliable.

"lang_id" was intended for the case just doing the language identification and no transcription, but it isn't very well tested or documented. It's not relevant for what you're trying to do, though.

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by jongwook
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