Diachronic OCR challenge
Do OCR of a Polish historical text (or post-correction of Tesseract OCR) [ver. 1.0.0]
Git repo URL: git://gonito.net/diachronia-ocr / Branch: master
Run git clone --single-branch git://gonito.net/diachronia-ocr -b master to get the challenge data
Browse at https://gonito.net/gitlist/diachronia-ocr.git/master
Leaderboard
# | submitter | when | ver. | description | test-A CharMatch | × | |
---|---|---|---|---|---|---|---|
1 | p/tlen | 2022-07-07 16:06 | 1.0.0 | Lucene Transducers ver. 0.27-SNAPSHOT rule-based | 56.4 | 2 | |
2 | s444415 | 2023-01-05 14:59 | 1.0.0 | Donut fine tune with data from challange fine-tuned donut proto ocr | 43.2 | 6 | |
3 | p/tlen | 2022-07-07 15:30 | 1.0.0 | just copy the Tesseract output tesseract | 33.7 | 2 | |
4 | s444415 | 2022-12-22 10:18 | 1.0.0 | Donut base model base donut | 26.2 | 6 |