myhloli e41e58e646 Update version.py with new version

2024-06-25 09:56:31 +00:00

..

cli

fix:use deepcopy keep the original model json

2024-06-25 16:18:38 +08:00

dict2md

fix:use line_lang instead of content_lang to concatenate para

2024-06-19 12:54:54 +08:00

filter

update: Enhance the capability to detect garbled document issues

2024-06-19 16:03:21 +08:00

layout

…

libs

Update version.py with new version

2024-06-25 09:56:31 +00:00

model

update custom model framework

2024-06-18 14:45:23 +08:00

para

fix:close some log output if not in debug mode

2024-06-25 16:42:12 +08:00

pipe

update: Enhance the capability to detect garbled document issues

2024-06-19 16:03:21 +08:00

post_proc

1、Trace类的key增加前置下划线

2024-04-11 17:43:00 +08:00

pre_proc

fix:close some log output if not in debug mode

2024-06-25 16:42:12 +08:00

rw

add errors="replace" in write mode MODE_TXT

2024-05-15 14:30:16 +08:00

spark

delete useless files

2024-06-25 11:15:50 +08:00

train_utils

feat: modify foot note bbox tmp

2024-03-23 14:34:25 +08:00

__init__.py

…

pdf_parse_by_ocr.py

renamed pipeline file name

2024-06-25 14:42:43 +08:00

pdf_parse_by_txt.py

renamed pipeline file name

2024-06-25 14:42:43 +08:00

pdf_parse_for_train.py

切图逻辑重构

2024-04-16 09:41:31 +08:00

pdf_parse_union_core.py

add todo about interline_equation

2024-06-07 11:11:34 +08:00

user_api.py

renamed pipeline file name

2024-06-25 14:42:43 +08:00