schift-io/KoOCR-Bench download history
schift-io/KoOCR-Bench is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 737 times (175 in the last 7 days), and 1,062 times in total. It ranks #34,958 among datasets by monthly downloads.
KoOCR-Bench v1.2 한국어 문서 OCR·문서 파싱 벤치마크입니다. 실제 한국 문서 623쪽(7개 영역)으로 글자, 표, 제목, 읽기 순서, 좌표를 함께 평가합니다. 평가 전용입니다. 학습에 쓰지 마세요. A Korean document OCR / parsing benchmark: 623 real Korean pages in 7 slices, scoring text, HTML tables, headings, reading order and block boxes. Evaluation only.
Open schift-io/KoOCR-Bench on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.