New v1.1 TATR checkpoints are now on Hugging Face - Githubissues

microsoft / table-transformer

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.

MIT License

2.01k stars 231 forks source link

New v1.1 TATR checkpoints are now on Hugging Face #158

Closed NielsRogge closed 6 months ago

NielsRogge commented 7 months ago

Hi there,

The new v1.1 TATR checkpoints are now available on Hugging Face's hub:

A demo notebook is available here which showcases detection, structure recognition and OCR: https://github.com/NielsRogge/Transformers-Tutorials/blob/master/Table%20Transformer/Inference_with_Table_Transformer_(TATR)_for_parsing_tables.ipynb.

A demo Space is available here (showcasing what's done in the notebook end-to-end): https://huggingface.co/spaces/nielsr/tatr-demo. It looks as follows:

tatr

bsmock commented 6 months ago

Great to see---thanks, Niels!

If anyone has a question about this, please direct it to one of the community forums on Hugging Face.

Cheers, Brandon