making it prettier

interfaces/cap_minor_media.py

@@ -142,11 +142,11 @@ def predict_cap(text, language, domain):
 description = """
 You can choose between two approaches for making predictions:
 
-1. **Hierarchical Classification**  
-   First, the model predicts a **major topic**. Then, a second model selects the most probable **subtopic** from within that major topic's category.
+**1. Hierarchical Classification**  
+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.
+**2. Flat Classification (single model)**  
+A single model directly predicts the most relevant label from all available classes, without distinguishing between major and subtopics.
 """
 
 demo = gr.Interface(