Request for Evaluation Code on Benchmarks (MMAU, Entailment, etc.)

[Jingchensun]

Hi, thanks for the great work!

Could you please release the evaluation code for the benchmarks used in the paper, including MMAU, Audio Entailment, Audio Difference, Audio Question-Answering, and Audio Captioning?

I tried reproducing the MMAU results with the released model but got significantly lower scores. Having the official evaluation scripts would be really helpful.

Thanks!

[soham97]

Hi @Jingchensun, for MMAU evaluation, this comment and reference code will be helpful: #5 (comment)