Sreyan88/RECAP

Code for ICASSP 2024 Paper: RECAP: Retrieval-Augmented Audio Captioning

14
/ 100
Experimental

This system helps you automatically describe audio content in plain language, even for sounds it hasn't encountered before. You provide an audio clip, and it generates descriptive text captions. This is ideal for sound archivists, media analysts, or content creators who need to categorize or understand vast collections of audio.

No commits in the last 6 months.

Use this if you need to generate accurate, detailed text descriptions for a wide variety of audio events, including novel or complex sounds, without extensive fine-tuning.

Not ideal if you primarily need to transcribe speech or identify specific musical elements rather than general environmental or event sounds.

audio-analysis sound-classification content-cataloging media-description acoustic-monitoring
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

Last pushed

Jun 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/Sreyan88/RECAP"

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