Skip to content

README.md

Latest commit

 

History

History
48 lines (35 loc) · 1.57 KB

README.md

File metadata and controls

48 lines (35 loc) · 1.57 KB
Raw

Sentiment2Music

This simple program analyzes the sentiment of sentences typed by the user, and composes music on-the-fly based on the extracted sentiment.

Dependencies

  • Python 2.7
  • NLTK 3.0, a natural language processing library. Installation.
  • FluidSynth 1.1, a real-time synthesizer. Installation. Also available via Homebrew.
  • PyFluidSynth 1.2, Python wrapper for FluidSynth. Installation. Also available via pip.

Installation

After installing the dependency tools/libraries mentioned above, clone this repository into a directory of your choice:

git clone git@github.com:erdiaker/sentiment2music.git

Sentiment analyzer needs some data (~15 MB) to train. Download it by typing the following in terminal:

python -m nltk.downloader movie_reviews punkt

FluidSynth needs some soundfont files (~145 MB) in order to synthesize sound. Download it into your installation directory as follows:

wget -O - http://ftp.de.debian.org/debian/pool/main/f/fluid-soundfont/fluid-soundfont_3.1.orig.tar.gz | tar -xzf -

Running Sentiment2Music

To start the program, type the following in your installation directory:

python sentiment2music.py

After a few seconds, you should start hearing something. The program will also prompt you to type a sentence. Do as instructed, and the music will change according to the sentiment of the sentence. Have fun!

License

MIT