wehub-resource-sync
14 lines
497 B
Markdown
14 lines
497 B
Markdown
# Qwen 2.5 OCR
|
|
|
|
**[WORK IN PROGRESS]**
|
|
|
|
A Streamlit-based application for Optical Character Recognition using the Qwen 2.5 VL (Vision-Language) model.
|
|
|
|
## Overview
|
|
|
|
This application provides a user-friendly interface for extracting and analyzing text from images using the powerful Qwen 2.5 VL model. It offers two primary modes of operation:
|
|
|
|
1. **Full Page OCR**: Extract all text content from an uploaded image
|
|
2. **Text Spotting**: Detect and visualize text with bounding boxes in the image
|
|
|