ebouteillon/freesound-audio-tagging-2019

Freesound Audio Tagging 2019

41
/ 100
Emerging

This solution helps machine learning practitioners automatically categorize audio recordings into multiple labels, even with limited manually-labeled data. It takes in collections of audio clips and associated labels, then outputs a system capable of accurately predicting what sounds are present in new, unseen audio. This is ideal for researchers or engineers working on advanced audio analysis projects.

No commits in the last 6 months.

Use this if you need a high-performing system to classify environmental sounds, animal sounds, or other audio events from raw sound files, especially when you have a mix of clean and noisy labeled data.

Not ideal if you're looking for a simple tool to tag a small number of audio files manually or if your primary goal is speech recognition.

audio-tagging sound-event-detection machine-listening audio-classification data-augmentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

95

Forks

15

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 28, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ebouteillon/freesound-audio-tagging-2019"

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