-
Notifications
You must be signed in to change notification settings - Fork 9.5k
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
Ocricola (H)FST support #15
Conversation
…alse by default in Tesseract
Things to do:
|
…ished_dawg is not/will not be implemented, add a note
I don't think it is going to happen. |
Not needed. The new engine works well with the dawgs. |
This is intended more to be an alternative to dawgs for morphologically complex languages that have a morphology available in HFST format. |
@mpsilfve do you have anything to add? |
How can we track this pull request and also #31? I think both should be considered for a future release of Tesseract. |
There are still branches with this code. IMHO if ray with go with dawgs alternatives will not very used... For several years nothing happened in this way and I am afraid that this will be in future the same. |
|
This adds support from the ocricola project to use finite state transducers in HFST format instead of DAWGs.
Branch is currently quite stale, but while I'm pulling all these pull requests together, I thought I should put this one in too.