PyPI page
Home page
Author:
None
License:
MIT
Summary:
CLI tool for extracting text with DeepSeek OCR and generating datasets
Latest version:
4.1.3
Required dependencies:
aiofiles
|
beautifulsoup4
|
click
|
datasets
|
ebooklib
|
httpx
|
mcp
|
openai
|
pillow
|
pyarrow
|
pymupdf
|
python-dotenv
|
python-pptx
|
rapidfuzz
|
rich
|
tqdm
Optional dependencies:
accelerate
|
addict
|
beautifulsoup4
|
black
|
easydict
|
ebooklib
|
einops
|
flash-attn
|
img2pdf
|
mypy
|
numpy
|
pymupdf
|
pytest
|
pytest-asyncio
|
ruff
|
tokenizers
|
torch
|
transformers
Downloads last day:
10
Downloads last week:
76
Downloads last month:
162