README.md

metadata

title: Gregg Shorthand Recognition
emoji: 🖋️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: mit
tags:
  - gregg-shorthand
  - handwriting-recognition
  - ocr
  - stenography
  - historical-documents
  - computer-vision
  - pytorch
models:
  - a0a7/gregg-recognition

Gregg Shorthand Recognition Space

This is an interactive demo for recognizing Gregg shorthand notation from images.

Features

• Upload images containing Gregg shorthand
• Real-time text recognition
• Confidence scoring
• Support for various image formats
• Historical document processing

How to Use

1. Upload an image containing Gregg shorthand notation
2. Adjust the confidence threshold if needed
3. Click "Recognize" to process the image
4. View the recognized text and confidence score

Model Information

This demo uses the Gregg Recognition model trained specifically for Gregg shorthand notation. The model combines:

• Convolutional Neural Networks (CNN) for feature extraction
• Long Short-Term Memory (LSTM) networks for sequence modeling
• Advanced pattern recognition techniques
• Specialized preprocessing for shorthand symbols

About Gregg Shorthand

Gregg shorthand is a system of stenography invented by John Robert Gregg in 1888. It was widely used for:

• Court reporting
• Business correspondence
• Note-taking
• Administrative documentation

This model helps digitize historical shorthand documents and assists in stenography education.

Technical Details

• Model Type: Image-to-Text Recognition
• Architecture: CNN-LSTM with Pattern Database
• Input Size: 256x256 pixels
• Framework: PyTorch
• Preprocessing: Grayscale conversion, normalization

Repository

Source code and model details: GitHub Repository