Sreyan88/CompA

Code for ICLR 2024 Paper: CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models

22
/ 100
Experimental

This project helps researchers and developers working with audio-language models improve how well these models understand complex audio descriptions. It takes existing audio-language models and structured audio datasets as input, and outputs enhanced models that are better at recognizing nuanced combinations of sounds and attributes. Audio AI researchers, machine learning engineers, and deep learning practitioners focused on audio applications would find this useful.

No commits in the last 6 months.

Use this if you are developing or researching audio-language models and need to improve their ability to understand complex, multi-faceted audio events and their descriptions.

Not ideal if you are an end-user looking for a pre-built application or a tool for general audio analysis, rather than a research framework for model improvement.

audio-language-modeling compositional-AI deep-learning-research sound-event-recognition AI-model-training
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

22

Forks

2

Language

Python

License

Last pushed

Jul 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Sreyan88/CompA"

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