Replies: 1 comment
-
Same issue |
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.
-
I use medium model to do transcribe task. Then I found some results were repeated. I tried to set a lower compression_ratio_threshold and set temperature to 0, but the problem still exists.


The I print the result details, I found that if it has two segments, the final text will combine the results from each segment and repeat twice. As shown in pictures, the red one shows how it repeat, and the blue one shows it has two segments.
How can I slove this problem?
Beta Was this translation helpful? Give feedback.
All reactions