> By checking the "Training" instruction page and seeing what the > current code can do, the farthest I got was "retrain=1 ocropus > trainseg <cmodel> <bookdir>", but I got the impression it just > replaced the old cmodel.
"retrain" just changes the naming convention used by If you want to continue training an existing model, you need to use linerec_cpreload; this is used for book adaptation, for example. It works quite well (see the publications). > That language modeling might be another story, but cmodel training > would be a start. For adding words to the language model, you need OpenFST in general (since you want to use operations like minimization). You can code that either in C++ or using a Python script using the pyopenfst bindings (project on Google 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 -~----------~----~----~----~------~----~------~--~---
