Spaces:
Running on Zero
Running on Zero
| title: PP-OCRv6 Medium Text Recognition | |
| emoji: 🔤 | |
| colorFrom: purple | |
| colorTo: gray | |
| sdk: gradio | |
| sdk_version: 6.15.1 | |
| app_file: app.py | |
| short_description: PP-OCRv6 medium recognition — text recognition from images | |
| python_version: "3.12" | |
| startup_duration_timeout: 30m | |
| # PP-OCRv6 Medium Text Recognition Demo | |
| This Space demonstrates [PP-OCRv6_medium_rec](https://huggingface.co/PaddlePaddle/PP-OCRv6_medium_rec), the medium-tier text recognition model from PaddlePaddle's PP-OCRv6 family. | |
| ## About | |
| PP-OCRv6_medium_rec is a 19M-parameter OCR recognition model that supports 50 languages. It takes a cropped image of a single text line as input and returns the recognized text string with a confidence score. | |
| ## Usage | |
| 1. Upload a cropped image of a single line of text (or try one of the examples) | |
| 2. Click "Recognize Text" | |
| 3. The recognized text, confidence score, and raw JSON output will appear | |
| ## Links | |
| - [Model card](https://huggingface.co/PaddlePaddle/PP-OCRv6_medium_rec) | |
| - [PaddleOCR GitHub](https://github.com/PaddlePaddle/PaddleOCR) | |
| - [PaddleOCR documentation](https://paddlepaddle.github.io/PaddleOCR/latest/en/index.html) |