Update README.md

README.md

@@ -48,8 +48,8 @@ This is due to the diverse nature of the AudioSet dataset used for pre-training,
 
 ## Citation
 
-If you use these pre-trained models in your work, please cite the following:
-Arxiv version of the paper [arxiv.org/abs/2405.00934](arxiv.org/abs/2405.00934)
+If you use these pre-trained models in your work, please cite the following
+
 
 ```bib
 @article{ARCH,
@@ -58,4 +58,6 @@ Arxiv version of the paper [arxiv.org/abs/2405.00934](arxiv.org/abs/2405.00934)
   year={2024},
   booktitle={2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)}, 
 }
-```
+```
+
+[arXiv version: arxiv.org/abs/2405.00934](arxiv.org/abs/2405.00934)