-
Notifications
You must be signed in to change notification settings - Fork 110
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
Add fast_beam_search_nbest for streaming pruned rnn-t #82
Add fast_beam_search_nbest for streaming pruned rnn-t #82
Conversation
@csukuangfj It is not done yet. However, I did some refactoring to have a clearer way to pass parameter to beam search. Please let me know what you think about it. Then I will add the same changes (if you agree) to the other models. |
@csukuangfj The doc is not update, I will do so, if you agree with the changes |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks!
The refactoring looks good to me.
@ezerhouni FYI: You can re-trigger the CI by removing the label https://github.com/k2-fsa/sherpa/runs/7502556741?check_suite_focus=true
|
I add icefall as a dependency in the CI. I restarted the workflow. Let see |
@csukuangfj any idea why the CI jobs are queued for more than an hour now ? |
Now, it is started. For each test, if there are more than two jobs, I just canceled all but the latest one. |
@csukuangfj I think the CI passed. Is it good to go ? |
Merging it then. Thanks @csukuangfj for your review |
Thanks! |
No description provided.