How to handle very long audio?

#3
by httpwwwfszyc - opened

Dear all,

I have an one-hour to transcribe, which is german audio.

Here I would like to know: is there any way to use such model to overcome the OOM problem?

Btw, is multi-gpu available on such tasks?

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment