Source code and datasets of paper: "VaeRL²: A VAE based Framework for Rap Lyrics Representation Learning".
Here are three folds corresponding to three experiments mentioned in the paper:
- nextline: Nextline Prediction;
- song_generate: Dope-Lyrics Generation;
- classification: Rap Genre Classification.
The experiment of parameter discussion is not summed up into a folder. It can be done with folder nextline by just modifying the corresponding parameters.
- Python 3.5
- Tensorflow == 1.1.0
- Keras == 2.0