Caa Eval

Benchmarks large audio-language models against adversarial audio attacks using the CAA dataset, computing WER, ROUGE-L, cosine similarity, and coherence scores to assess robustness in conversational settings.

qhjqhj00 Updated 3 repo stars

File contents

qhjqhj00/research-skills-pool commit 4ba41f4dc0

Frequently asked questions

npx get-skill add qhjqhj00/caa-eval