Benchmark Dataset - independent, rights-cleared HTR corpus for Congress Poland Jewish vital records; corpus in preparation, evaluator runnable now.

benchmark benchmark-dataset dataset digital-humanities genealogy handwritten-text-recognition ocr polish-history python
1 Open Issue Need Help Last updated: Aug 12, 2026

Open Issues Need Help

View All on GitHub

Benchmark Dataset - independent, rights-cleared HTR corpus for Congress Poland Jewish vital records; corpus in preparation, evaluator runnable now.

Python
#benchmark#benchmark-dataset#dataset#digital-humanities#genealogy#handwritten-text-recognition#ocr#polish-history#python