| --- |
| license: mit |
| --- |
| |
| # Table Structure Recognition Model for [Pix2Text (P2T)](https://github.com/breezedeus/Pix2Text) |
|
|
| Currently, this model is forked from https://huggingface.co/microsoft/table-transformer-structure-recognition-v1.1-all (much thanks to the authors), and will be evolving afterward. |
|
|
| ## Documents for Pix2Text |
|
|
| - [Pix2Text V1.0 New Release: The Best Open-Source Formula Recognition Model | Breezedeus.com](https://www.breezedeus.com/article/p2t-v1.0) ; |
| - Pix2Text (P2T) Github: [breezedeus/pix2text](https://github.com/breezedeus/Pix2Text) ; |
| - Pix2Text Online Free Service: [p2t.breezedeus.com](https://p2t.breezedeus.com/) ; |
| - Pix2Text More: [breezedeus.com/pix2text](https://breezedeus.com/article/pix2text) ; |
|
|
| --- |
|
|
|
|
| Table Transformer (TATR) model trained on PubTables1M and FinTabNet.c. It was introduced in the paper [Aligning benchmark datasets for table structure recognition](https://arxiv.org/abs/2303.00716) by Smock et al. and first released in [this repository](https://github.com/microsoft/table-transformer). |
|
|
| Disclaimer: The team releasing Table Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. |
|
|
| ## Model description |
|
|
| The Table Transformer is equivalent to [DETR](https://huggingface.co/docs/transformers/model_doc/detr), a Transformer-based object detection model. Note that the authors decided to use the "normalize before" setting of DETR, which means that layernorm is applied before self- and cross-attention. |
|
|
| ## Usage |
|
|
| You can use the raw model for detecting tables in documents. See the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/table-transformer) for more info. |
