Skip to content
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 beam in RandEquivalent #46

Merged
merged 2 commits into from
May 29, 2020
Merged

Conversation

qindazhu
Copy link
Collaborator

No description provided.

@danpovey
Copy link
Collaborator

Haowen, the logic here is not right because if you do some kind of pruned algorithm on a that will discard arcs that are not within beam of the best path, that does not imply that no paths exist that are within beam of the best path. Think about a lattice with many confusable parts, one after another.

@qindazhu
Copy link
Collaborator Author

yes, you are right, thanks! Changed title to wip and will work on it later

@qindazhu qindazhu changed the title add beam in RandEquivalent [WIP] add beam in RandEquivalent May 27, 2020
@qindazhu qindazhu changed the title [WIP] add beam in RandEquivalent add beam in RandEquivalent May 28, 2020
@danpovey danpovey merged commit d860c7e into k2-fsa:master May 29, 2020
@qindazhu qindazhu deleted the haowen-fsa-test branch May 29, 2020 06:58
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants