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 -~----------~----~----~----~------~----~------~--~---
