Pretrained Models for reproducibility

minguinho26 / Prefix_AAC_ICASSP2023

Official Implementation of "Prefix tuning for Automated Audio Captioning(ICASSP 2023)"

https://prefixaac.github.io

23 stars 2 forks source link

Pretrained Models for reproducibility #9

Open v-manhlt3 opened 2 months ago

v-manhlt3 commented 2 months ago

Hi,

First of all, your project is great and I am working on this project. However, I am not able to reproduce your results reported in the ICASSP paper. It would be great if you could share your pre-trained models for reproducibility.

Thanks!

minguinho26 commented 4 weeks ago

Hi, sorry for writing a comment to you late.

You can download the pretrained files by doing the following intruction in README.md

Also, I found that the performance differ if you use GPU that not have tensor core. If you can't generate same (or similar) performance, I recommend to check your GPU's speficifation.

Thank you