albumentations
bs4
cn2an
cachetools
datrie
effdet
hanziconv
html_text
lxml
layoutparser
nougat-ocr
nltk
opencv-python
openpyxl
onnxruntime
pdfplumber
pyclipper
PyPDF2
python-docx
python-pptx
ruamel.yaml
roman-numbers
shapely
StrEnum
tika
tiktoken
transformers
tokenizers
word2number
xgboost
langdetect
