making it even prettier

interfaces/cap_minor_media.py

@@ -146,7 +146,7 @@ You can choose between two approaches for making predictions:
 First, the model predicts a **major topic**. Then, a second model selects the most probable **subtopic** from within that major topic's category.
 
 **2. Flat Classification (single model)**  
-A single model directly predicts the most relevant label from all available classes, without distinguishing between major and subtopics.
+A single model directly predicts the most relevant label from all available classes (both media and minor topics).
 """
 
 demo = gr.Interface(