cvondrick/soundnet

SoundNet: Learning Sound Representations from Unlabeled Video. NIPS 2016

50
/ 100
Established

This project helps you understand and categorize sounds in your audio files by leveraging a pre-trained model derived from millions of unlabeled videos. You provide MP3s or other audio files, and it tells you what objects or scenes are likely present in the sound, or it extracts detailed sound features for further analysis. It's ideal for researchers or practitioners working with environmental audio, soundscapes, or multimedia content.

464 stars. No commits in the last 6 months.

Use this if you need to automatically identify objects or scenes from audio, or extract meaningful feature representations from sound for tasks like indexing, searching, or classification without extensive manual labeling.

Not ideal if you're looking for a simple, out-of-the-box application with a graphical interface, or if your primary interest is speech recognition or music analysis.

audio-analysis soundscape-ecology environmental-monitoring multimedia-content-analysis acoustic-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

464

Forks

94

Language

Lua

License

MIT

Last pushed

Oct 07, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cvondrick/soundnet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.