This is a system for classifying audio files by music genre. Utilizing Essentia for audio analysis and TensorFlow for machine learning, it delivers high accuracy and efficiency in genre prediction.

Installation

Make sure you have Docker installed.

Clone & navigate:

git clone https://github.com/avrtt/music-classification-benchmark.git
cd music-classification-benchmark

Build and run the Docker container:

docker build -t music-classification-benchmark .
docker run -it -p 8000:8000 music-classification-benchmark

Usage

Once the Docker container is running, you can navigate to the Swagger API interface to upload an audio file for classification:

http://localhost:8000/docs#/

Contributing

Feel free to open PRs and issues.

License

This project is licensed under the MIT License, allowing free use, modification, and distribution. See the LICENSE file for more information.