PaddleOCR

History

co63oc de12ece0aa Fix (#14798 )		2025-03-04 11:04:41 +08:00
..
kie_dict	…
layout_dict	…
unimernet_tokenizer	…
README.md	Fix (#14798 )	2025-03-04 11:04:41 +08:00
ar_dict.txt	…
arabic_dict.txt	…
be_dict.txt	…
bengali_dict.txt	…
bg_dict.txt	…
bm_dict.txt	…
bm_dict_add.txt	…
bn_dict.txt	…
chinese_cht_dict.txt	…
confuse.pkl	…
cyrillic_dict.txt	…
devanagari_dict.txt	…
en_dict.txt	…
fa_dict.txt	…
french_dict.txt	…
german_dict.txt	…
gujarati_dict.txt	…
hebrew_dict.txt	…
hi_dict.txt	…
it_dict.txt	…
japan_dict.txt	…
ka_dict.txt	…
kazakh_dict.txt	…
korean_dict.txt	…
latex_ocr_tokenizer.json	…
latex_symbol_dict.txt	…
latin_dict.txt	…
mr_dict.txt	…
ne_dict.txt	…
oc_dict.txt	…
parseq_dict.txt	…
ppocrv4_doc_dict.txt	…
pu_dict.txt	…
rs_dict.txt	…
rsc_dict.txt	…
ru_dict.txt	…
samaritan_dict.txt	…
spin_dict.txt	…
syriac_dict.txt	…
ta_dict.txt	…
table_dict.txt	…
table_master_structure_dict.txt	…
table_structure_dict.txt	…
table_structure_dict_ch.txt	…
te_dict.txt	…
th_dict.txt	Add Thai character dictionary for OCR recognition (#14620 )	2025-02-05 16:09:49 +08:00
ug_dict.txt	…
uk_dict.txt	…
ur_dict.txt	…
vi_dict.txt	…
xi_dict.txt	…

README.md

Dictionary and Corpus

Dictionary files (usually character level vocabulary) are included here for easier configuration. Corpus contributed by OSS contributors are listed here, please respect copyrights when using them at your own risk.

Burmese corpus: https://github.com/1chimaruGin/BurmeseCorpus