Honee-W/U-SAM

Official repository for U-SAM (Interspeech 2025)

30
/ 100
Emerging

U-SAM helps researchers and developers working with audio by providing a single system to understand speech, general audio, and music. It takes raw audio inputs and can interpret what's happening within those sounds, allowing for a wide range of audio-language applications. This is for anyone creating tools or systems that need to process and understand diverse types of audio content.

No commits in the last 6 months.

Use this if you are developing applications that need to interpret or categorize different types of audio, from spoken words to musical compositions and environmental sounds.

Not ideal if you are an end-user looking for a ready-to-use application; this is a foundational model for developers to build upon.

audio-analysis speech-recognition music-information-retrieval sound-event-detection audio-language-processing
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

26

Forks

4

Language

Python

License

Last pushed

Jun 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Honee-W/U-SAM"

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