This project focuses on detecting cough events from audio data using deep learning models. Two main approaches were explored: a 1D Convolutional Neural Network (CNN) and the Audio Spectrogram Transformer (AST). The project includes data preprocessing, model training, and evaluation pipelines.
├── 1D_CNN_Model.py # Python script implementing 1D CNN model ├── AST.ipynb # Notebook implementing AST-based classifier ├── DataPreprocessing.ipynb # Data cleaning, segmentation, and feature extraction ├── Project_Report.pdf # Final report summarizing objectives, methods, and results └── dataset/ # Folder containing audio data or metadata (not included in repo)
How to Run step 1: Clone the repository: git clone https://github.com/your-username/Cough-Detection.git cd Cough-Detection step 2: Preprocess the data Open and run DataPreprocessing.ipynb to extract and format features. step 3: Train models Run 1D_CNN_Model.py to train a CNN model. or open AST.ipynb to run the transformer-based model.