Skip to content

BSVogler/music-genre-recognition-pipeline

master
Switch branches/tags
Code
This branch is 159 commits ahead of amirothman:master.
Contribute

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.

Music Genre Classification Pipeline

The pipeline is managed with python. The webAPI can be accessed with a web view.

webAPI → youtube-dl
                 ↓
webAPI ← keras ← vamp

Demo Video

Current known issues: The webserver does not serve python files.

Model

The deep learning model uses convolution on top of recurrent cells. It achieves an accuracy (precision) of 85% on three genres.

Confusion Matrix

Dataset

The datset is included in the form of pickled feature vectors extracted via sonic-annotator. The original music files and categorization were collections of "best-of" music CDs.

Dependencies

youtube-dl, sonic-annotator with plug-ins

Detailed guide in tutorial.md

Feature Extractions

On Mac OS copy the plugins to /Library/Audio/Plug-Ins/Vamp/.

allow execution of unsigned library in security settings after a failed attempt

Python Dependencies

Simply run:

sudo python3 -m pip install -r requirements.txt

About

A tool to detect the music genre using machine learning with keras.

Topics

Resources

License

Stars

Watchers

Forks

Languages

  • Python 83.4%
  • HTML 8.4%
  • Shell 6.1%
  • CSS 2.1%