Sunday, August 24, 2025
Show HN: A lightweight ML model to predict music emotion - energy, valence, etc. https://ift.tt/LdoKQf7
Show HN: A lightweight ML model to predict music emotion - energy, valence, etc. Spotify has 7 features for each of their music tracks (acousticness, danceability, energy, instrumentalness, liveness, speechiness, valence) which describe the perceptual/emotional content of the song. I wanted to tag my own offline music library with these features so that I could sort my songs into playlists for different occasions (working out, driving, etc.), but unfortunately Spotify doesn't share how they calculate these features. So, I trained my own lightweight neural network to predict these features! https://ift.tt/JXw8vx4 August 25, 2025 at 02:16AM
Subscribe to:
Post Comments (Atom)
Show HN https://ift.tt/LgJ3vuH
Show HN This is origintracer a low level observability tool of the modern web stack. It observes nginx, Gunicorn, asynchronous Python, Uvico...
-
Show HN: WebApp that blows water out of your phone's speakers https://ift.tt/2VmXkOf March 16, 2021 at 08:22AM
-
Show HN: Music player for big local collections with mpd support mpz is a C++/Qt music player focused on UX, with derectory tree and playlis...
-
Show HN: Stickerbox, a kid-safe, AI-powered voice to sticker printer Bob and Arun here, creators of Stickerbox. If AI were built for kids, w...
No comments:
Post a Comment