Update README.md

README.md

@@ -34,7 +34,7 @@ Our approach leverages *CLIP* as a prior for perceptual tasks, inspired by cogni
 
 ## Performance
 
-The model was trained on the *EmoSet dataset* using the common train, val, test splits and exhibits *state-of-the-art performance compared to previous methods.
+The model was trained on the *EmoSet dataset* using the common train, val, test splits and exhibits *state-of-the-art performance* compared to previous methods.
 
 ## Usage