A research project in conditional lyric generation conditioned on artists
This project uses conda to manage packages and requirements - however pip can also be used.
See setup.sh to get started and install requirements for the project
Important files relating to the dataset (train splits, artist list, token lists, etc) can be found in src/dataset
The dataset can be recreated from following the notebook src/dataset/dataset.ipynb
We forked Sennrich's BPE implementation here and BPE can be run using the notebook
For CVAE, we have a training notebook which demonstrates the commands needed to train the model and generate verses
For BART, we have a training repo artist-lyric-gen-bart
For BART, generation and perplexity (things needing the BART model) can be done following our notebook src/Generation + Perplexity ... .ipynb
All other metrics using the generated verses can be done following src/artist_gen_eval.ipynb