README.md

metadata

title: Table Extraction (Table Transformer + PaddleOCR)
emoji: 🚀
colorFrom: while
colorTo: black
sdk: streamlit
sdk_version: 1.21.0
app_file: app.py
pinned: false

huggingface-space

Imported from https://huggingface.co/spaces/jurgendn/table-extraction with some adjustment.

Current pipeline:

Table detection: https://huggingface.co/microsoft/table-transformer-detection

Table recognition: https://huggingface.co/microsoft/table-transformer-structure-recognition

OCR: https://github.com/pbcquoc/vietocr

OCR-new: https://github.com/PaddlePaddle/PaddleOCR