Me and Eric both wanted to learn how to freestyle rap, but were having trouble coming up with rhymes to write our next bars to, so we came up with this idea to help us out!
A major challenge we faced was processing the audio into text and generating rhymes in time for the next bar, which we did by using a local Vosk (voice recognition) model and the open-source CMU Pronouncing Dictionary (also local) to generate these suggestions in time.
We've also implemented some other QoL features, like loading beats into the program and controlling the playback speed, so users can vary the difficulty for themselves as they get faster.
Built With
- cmu-rhyming-dictionary
- python
- tkinter
- vosk
Log in or sign up for Devpost to join the conversation.