OCR challenge for index cards

The goal of this task is to post-process the output from the Tesseract OCR engine. Alternatively, it could be treated as an OCR, as images are also available. [ver. 1.0.2]

# submitter when ver. description dev-0 CER dev-0 WER dev-0 CharMatch test-A CER test-A WER test-A CharMatch
4 s444415 2023-03-23 11:49 1.0.2 Donut trained on wikisource fine-tuned donut ocr 1.038 0.991 0.370 1.000 1.000 0.401
6 s444415 2023-03-21 08:35 1.0.2 Donut fine tuned wikisource yellow fine-tuned donut ocr 1.021 1.010 0.367 1.066 1.122 0.370
2 s444415 2023-01-05 15:02 1.0.2 Donut fine tune with data from challange fine-tuned donut ocr 0.557 0.741 0.537 0.664 0.915 0.508
1 s444415 2022-12-22 13:58 1.0.2 Donut fine tuned fine-tuned donut 0.486 0.813 0.585 0.459 0.694 0.622
7 s444415 2022-12-22 13:51 1.0.2 Donut base model base donut 1.624 1.973 0.231 1.995 2.459 0.206
5 s444415 2022-12-22 13:46 1.0.2 Donut proto model donut proto 1.054 1.080 0.359 1.079 1.089 0.377
3 p/tlen 2021-04-09 16:01 1.0.1 Baseline - just rewrite Tesseract output baseline tesseract 0.432 0.745 0.422 0.463 0.786 0.425