IvanOjok/RuleGuidedQwen

This model is a LoRA finetuned Qwen model that employs production rules to ensure strict rule compliance with Grade2 Braille rules and outperforms a neural-only model on UEB compliance metrics like compliance, capitalization, punctuation, numeric, and OOV accuracy. These individual metrics form the model's recall. The precision score of the model (which accounts for character insertions in the outputs differing from references) is also significantly better than the stand-alone neural model.