Sound Classification

Repo - https://github.com/SidSaxena01/sound-classification/tree/main

---

This repository contains notebooks and code for working with audio embeddings and sound classification. They can be found in:

• Sound Classification or

• Embedding Extractor or

Alternatively, you can also open them in colab from the links provided.

Installation

1. Create a Python virtual environment:

   python -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate

2. Install the required dependencies:

   pip install -r requirements.txt

3. Download the required data:

   • Download the file amplab_machine_listening_module_data.zip from the shared folder
   • Place it in the repository root and unzip it
   • Make sure the uncompressed folder is named amplab_machine_listening_module_data

Running the Notebook

1. Start Jupyter:

   jupyter notebook

2. Open the notebook embedding_extractor.ipynb

3. Open the notebook sound_classification.ipynb

If you encounter package compatibility issues, run the cell with the setup script and restart the kernel.

Troubleshooting

If you encounter issues with dependencies:

1. Make sure you're using Python 3.9+ and have created a virtual environment
2. Run the setup script included in the notebook
3. Restart the kernel after installing dependencies
4. If problems persist, try uninstalling problematic packages and reinstalling them one by one