-
Notifications
You must be signed in to change notification settings - Fork 108
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Streaming server with context graph produces cut transcripts #504
Comments
Merged
Thanks! I will have a look at this issue. |
I'm having the same issue. It seems log_prob gets a big negative score and hyp with less tokens always "wins" which results in lost transcript. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Streaming server with context graph produces cut transcripts if the value of context-score exceeds some threshold (2.5 for example). This started to happen after commit #468. It can be reproduced with various model (conformer, zipformer) for lengthy audio and large context-score.
The text was updated successfully, but these errors were encountered: