Speech Command CNN Experiments

This repository contains Jupyter notebooks for training and evaluating convolutional neural networks on speech command classification tasks. The experiments compare three different activation functions: Tanh, ReLU, and Leaky ReLU.

What's included

• model_experiments.ipynb - Main notebook that runs experiments with all three activation functions
• experiments_tanh.ipynb - Focused experiments using Tanh activation only
• experiments_relu.ipynb - Focused experiments using ReLU activation only
• experiments_leaky_relu.ipynb - Focused experiments using Leaky ReLU activation only

Getting started

git clone https://github.com/yourusername/speech-command-cnn-notebooks.git
cd speech-command-cnn-notebooks
pip install -r requirements.txt
jupyter notebook

Open any notebook and update the dataset path, then run the cells.

License

MIT License