🎧 Algorhythm: Audio Segmentation & Classification

Algorhythm is a Python package for scalable, production-ready audio segmentation and classification, providing a consistent framework for orchestrating and comparing different algorithms across audio analysis workflows.

🚀 Features

• Modular pipelines: Compose end-to-end audio workflows from pre-processing through to segmentation and classification.
• Reusable components: Shared interfaces for different algorithms to simplify experimentation and benchmarking.
• Experiment-friendly design: Configuration-driven setup that supports reproducible research and rapid iteration.

🛠 Technologies Used

• Programming Language: Python
• Core Libraries: NumPy, SciPy, scikit-learn
• Testing & Tooling: Git, CI/CD pipelines

💡 Skills & Competencies Gained

• Package design: Architecting a clean, extensible API for research and production users.
• Audio ML workflows: Structuring pipelines for segmentation, feature extraction, and classification.
• Open-source distribution: Packaging, versioning, and publishing a library on PyPI with documentation and tests.

🔗 Links

The project is fully open source, with the GitHub repository hosting the codebase, issue tracking, and development workflow, while the PyPI package provides a convenient installation route for users who want to integrate Algorhythm directly into their audio analysis pipelines.