Replies: 1 comment
-
Usually running Whisper with Whisper seemed to do okay until hallucinating some profane self-hatred from My results - click to expand!
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
https://youtu.be/L3ZguNkBbao
Aside from a few errors, there are parts where, for example, there is noise in the background, but generates entire chunks of words as to repeat the last segments. This is very apparent from 02:51.000 to 03:00.000 and other similar areas. This video is a good example of a noisy video with music in an attempt to transcribe lyrics. It really put the medium model to the test.
Beta Was this translation helpful? Give feedback.
All reactions