Update README.md

README.md

@@ -42,11 +42,10 @@ the first-order Ambisonics format.
 - **Language(s) (NLP):** GRAMs support all languages, but mainly English.
 - **License:** MIT
 
-### Model Sources [optional]
-
+### Model Sources
 
 - **Repository:** https://github.com/labhamlet/GRAM-T
-- **Paper [optional]:** https://arxiv.org/abs/2506.00934
+- **Paper:** https://arxiv.org/abs/2506.00934
 
 ## Uses
 
@@ -119,7 +118,7 @@ initial learning rate was set to 0.0002, and decayed to 0. We optimize the mean
 loss function between the predicted masked patches and their corresponding input spectrogram
 patches.
 
-#### Preprocessing [optional]
+#### Preprocessing
 
 Firstly, RMS Normalization was applied to audio clips to get all of them in the same loudness levels. Later, instance normalization was applied to the convolved scenes