Spaces:
Running
on
Zero
Running
on
Zero
Jordan Legg
commited on
Commit
•
b153fc4
1
Parent(s):
aa072c3
refactor: make title and description easier to use
Browse files- content/index.md +53 -0
content/index.md
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: "🙋🏻♂️Welcome to Tonic's🫴🏻📸GOT-OCR"
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# GOT-OCR Model Overview
|
| 6 |
+
|
| 7 |
+
The **GOT-OCR model** is a cutting-edge OCR system with **580M parameters**, designed to process a wide range of "characters." Equipped with a **high-compression encoder** and a **long-context decoder**, it excels in both scene and document-style images. The model supports **multi-page** and **dynamic resolution OCR**, enhancing its versatility.
|
| 8 |
+
|
| 9 |
+
### Output Formats
|
| 10 |
+
|
| 11 |
+
The model can generate results in several formats:
|
| 12 |
+
|
| 13 |
+
- **Plain Text**
|
| 14 |
+
- **Markdown**
|
| 15 |
+
- **TikZ diagrams**
|
| 16 |
+
- **Molecular SMILES strings**
|
| 17 |
+
|
| 18 |
+
Additionally, **interactive OCR** enables users to define regions of interest via **coordinates** or **colors**.
|
| 19 |
+
|
| 20 |
+
## Key Features
|
| 21 |
+
|
| 22 |
+
- **Plain Text OCR**: Extracts text from images.
|
| 23 |
+
- **Formatted Text OCR**: Retains the original formatting, including tables and formulas.
|
| 24 |
+
- **Fine-grained OCR**: Offers box-based and color-based OCR for precision in specific regions.
|
| 25 |
+
- **Multi-crop OCR**: Handles multiple cropped sections within an image.
|
| 26 |
+
- **Rendered Formatted OCR**: Outputs in markdown, TikZ, SMILES, and more, with rendered formatting.
|
| 27 |
+
|
| 28 |
+
## Supported Content Types
|
| 29 |
+
|
| 30 |
+
- Plain text
|
| 31 |
+
- Math/molecular formulas
|
| 32 |
+
- Tables and charts
|
| 33 |
+
- Sheet music
|
| 34 |
+
- Geometric shapes
|
| 35 |
+
|
| 36 |
+
## How to Use
|
| 37 |
+
|
| 38 |
+
1. Select a task from the dropdown menu.
|
| 39 |
+
2. Upload an image.
|
| 40 |
+
3. (Optional) Adjust parameters based on the selected task.
|
| 41 |
+
4. Click **Process** to view the results.
|
| 42 |
+
|
| 43 |
+
### Model Information
|
| 44 |
+
|
| 45 |
+
- **Model Name**: GOT-OCR 2.0
|
| 46 |
+
- **Hugging Face Repository**: [ucaslcl/GOT-OCR2_0](https://huggingface.co/ucaslcl/GOT-OCR2_0)
|
| 47 |
+
- **Environment**: CUDA 11.8 + PyTorch 2.0.1
|
| 48 |
+
|
| 49 |
+
---
|
| 50 |
+
|
| 51 |
+
### Join us :
|
| 52 |
+
|
| 53 |
+
🌟TeamTonic🌟 is always making cool demos! Join our active builder's 🛠️community 👻 [](https://discord.gg/qdfnvSPcqP) On 🤗Huggingface:[MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to🌟 [Build Tonic](https://git.tonic-ai.com/contribute)🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗
|