I created a new Google Code project for Python bindings to the OpenFST
library.  It's pretty new code, but it seems to be working.  There are
some sample scripts.  If you're trying to build language models, this
is probably a good starting point.

Note that this is not the code we've been using to build language
models so far, but we're going to be switching to something Python
based, also to make it easier for people to change the language
modeling and apply it to their own data.

If you want to contribute, some parts that would be useful would be
porting the A* and beam search decoders from OCRopus directly this (so
that they are available separately from OCRopus), actual language
modeling tools (in Python if you like), and any kind of training and
estimation code.

Tom

--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"ocropus" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to 
[email protected]
For more options, visit this group at 
http://groups.google.com/group/ocropus?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to