LibROSA is a python package for music and audio analysis , it provides the building blocks necessary to create music information retrieval systems .

Out of sound clips provided under training instances , 38 of Mel Frequency cepstral coefficients(.mfcc) are extracted/saved and then comapred with the existing presets .

animals : A test animal sound clip is fed to the program , it detects and prints the name of the animal .

voice : A test human sound clip is fed to the prgram , it detects and prints the gender of the speaker .

music : A test sound piece is fed to the program and it detects which genre of music it is .

• install LibROSA
• install PyAudio
• install SciPy and Numpy .

pip3 install numpy
pip3 install scipy

• This repository / project was a part of [Mumbai Hackathon 2017](https://mumbaihackathon.in/winners)

• This project was done under 24 hours with minimal pre-preparation
• Here number of training instances were low in reference to time limit provided .

• @praffulj4199
• @divyakhetan
• @ahaanshetty
• @pravar98
• @inishchith