Skip to content

Choose a prolific rapper, seed the AI with a word or phrase, and it will auto-generate verses in the style of the chosen artist.

License

Notifications You must be signed in to change notification settings

UpwardTrajectory/auto-rapper

Repository files navigation

Auto-rapper:

This is a Rap generator that has adjustable styles, lengths, and "temperature" aka randomness. Optionally, the user can train new models that will match the style of any input text (this takes some time). Also, the user can input a starting text, similar to talk to transformer

The Data

We have access to lyrics from all publicly available songs.

The Plan

Access the Genius.com API through the lyricsgenius python package to get lyrics from prolific rappers, then train models to learn the unique styles of each.

The Preperation

Take lyrics from all songs by each rapper and place them in unique .txt files to be used when fine tuning the model. Put lyricsgenius functions into .py files for simplicity.

The Modeling

We used google colab with a gpu to Retrain gpt-2's 345mb model on each of the rappers, then saved each uniquely retrained model for future use.

The Results

We have a simple generator that can make relatively cohesive raps based off of the chosen rapper's style and the prefix text.

Next steps

Ideally deploying the auto rapper to the web as a flask app would be nice, also increasing the number of rapper models

Where credit is due:

We borrow heavily from the code in this repo and this google colab which is also linked in the repo.

OpenAI's official GPT-2 repo (MIT License)

About

Choose a prolific rapper, seed the AI with a word or phrase, and it will auto-generate verses in the style of the chosen artist.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published