PyPI page
Home page
Author:
Dipankar
License:
MIT
Summary:
High-fidelity PDF parsing for chunkr: layout, headings, tables, page labels and OCR via liteparse
Latest version:
0.1.1
Required dependencies:
chunkr-rs
|
liteparse
Optional dependencies:
easyocr
|
numpy
|
onnxruntime
|
paddleocr
|
paddlepaddle
|
pillow
|
pytest
|
rapidocr
|
surya-ocr
Downloads last day:
6
Downloads last week:
244
Downloads last month:
0
7-day smoothing