First TrOCR adaptation for Tigrinya achieves 0.22% CER and 97.2% exact match using tokenizer extension plus Word-Aware Loss Weighting on 5000 synthetic GLOCR images.
Finetuning vision-language models as OCR systems for low-resource languages: A case study of Manchu, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adapting TrOCR for Printed Tigrinya Text Recognition: Word-Aware Loss Weighting for Cross-Script Transfer Learning
First TrOCR adaptation for Tigrinya achieves 0.22% CER and 97.2% exact match using tokenizer extension plus Word-Aware Loss Weighting on 5000 synthetic GLOCR images.