sarahkhudze/chichewa-sign-language-model-development

This repository contains the Jupyter Notebook used to develop and train a Convolutional Neural Network (CNN) model for Chichewa Sign Language recognition. # Chichewa Sign Language CNN Model Development 📘 This repository contains the Jupyter Notebook used to design, train, and evaluate a **Convolutional Neural Network (CNN)** for Chichewa Sign Language recognition. It is intended to complement the real-time detection application by showing how the deep learning model was built before deployment. --- ## 📁 What’s Inside - `train_csl_model.ipynb`: The full notebook showing: - Data loading and preprocessing - CNN architecture definition - Training and validation process - Model performance metrics - `data/`: Folder containing sign language image dataset (e.g., SL-MNIST or local CSL dataset) - `model/`: Trained TensorFlow `.h5` model file (`chichewa_sign_language.h5`) - `requirements.txt`: Python dependencies for reproducibility --- ## 🧠 Goal To document the development of a deep learning model for Chichewa Sign Language (CSL) using TensorFlow/Keras, and support its integration into a web-based gesture recognition system. --- ## 📊 Key Results | Metric | Value | Description | |--------|-------|-------------|