Skip to content

Identifying the genre of the music from the sound files using CNNs

Notifications You must be signed in to change notification settings

nikhiltitus/music-genre-recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Synopsis

This program recongnizes the genre of a music by listening directly to the sound files. Once the program is run an output.txt file is obtained which contains the name of the songs and the genre of the music. This can be used by any individual to organize their music library or this can be used for building recommender systems. The model was trained using keras on tensorflow to obtain an accuracy of about 75% on the FMA dataset.

This program can identify 8 genres: Hip-Hop,Pop,Folk,Experimental,Rock,International,Electronic,Instrumental

For more details on how the model was trained please refer my other repo: https://github.com/nikhiltitus/genre-recognition

Usage

Use it as:

python genre_classification location extension

python genre_classification.py data/genres mp3

Acknowledgements

Contact info

Please contact me: nikhiltitusk@gmail.com if you need any more info.

License

This code is released under MIT license: https://opensource.org/licenses/MIT

About

Identifying the genre of the music from the sound files using CNNs

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages