Inspiration
Boring pandemic days listening to background music on youtube channels gave rise to the idea of improving the music listening experience.
What it does
Based on machine learning models trained on a dataset, it identifies the mood of previously unseen music and plays it if it fits the mood of the local weather at your current location. This is a prototype for a smart music player.
How we built it
Open weather API. Adaboost on 300 songs.
Challenges we ran into
Nobody in the team is familiar with web dev so we had to learn as we go.
Accomplishments that we're proud of
0.8 test set accuracy on arousal classification and 0.7 on valence classification.
What we learned
How to build a website
What's next for ResonantFrequency
Apply the music mood identifier to many more things!
Log in or sign up for Devpost to join the conversation.