---
license: mit
base_model: microsoft/Phi-3.5-vision-instruct
tags:
- OCR
pipeline_tag: image-text-to-text
---

# TB-OCR: an end-to-end OCR model handling text, math latex, and markdown formats all at once

## Model Summary

TB-OCR-preview (Text Block OCR), created by [Yifei Hu](https://x.com/hu_yifei), is an end-to-end OCR model handling text, math latex, and markdown formats all at once. The model takes a block of text as the input and returns clean markdown output. Headers are marked with `##`. Math expressions are guaranteed to be wrapped in brackets `\( inline math \) \[ display math \]` for easier parsing. This model does not require line-detection or math formula detection. 

**Running the model in 4-bit only requires ~2.8GB VRAM to load and exhibits little to none degradation.**

This model is recommended to work with **TFT-ID-1.0**[[HF]](https://huggingface.co/yifeihu/TFT-ID-1.0), a text/tale/figure detection model, for full page document parsing.

![image/png](https://huggingface.co/yifeihu/TB-OCR-preview-0.1/resolve/main/tb-ocr-cover.png)

## Sample Usage