refactor the interface display

app.py

@@ -261,18 +261,18 @@ inputs = [
 
 outputs = [
     RichTextbox(label="Processed Text"),
-    gr.Audio(label="Audio Output (Native Language) 1"),
-    gr.Audio(label="Audio Output (Target Language) 1"),
-    gr.Audio(label="Audio Output (Native Language) 2"),
-    gr.Audio(label="Audio Output (Target Language) 2"),
-    gr.Audio(label="Audio Output (Native Language) 3"),
-    gr.Audio(label="Audio Output (Target Language) 3"),
     gr.Textbox(label="Focus 1"),
     gr.Textbox(label="Translated Phrases 1"),
+    gr.Audio(label="Audio Output (Native Language) 1"),
+    gr.Audio(label="Audio Output (Target Language) 1"),
     gr.Textbox(label="Focus 2"),
     gr.Textbox(label="Translated Phrases 2"),
+    gr.Audio(label="Audio Output (Native Language) 2"),
+    gr.Audio(label="Audio Output (Target Language) 2"),
     gr.Textbox(label="Focus 3"),
-    gr.Textbox(label="Translated Phrases 3")
+    gr.Textbox(label="Translated Phrases 3"),
+    gr.Audio(label="Audio Output (Native Language) 3"),
+    gr.Audio(label="Audio Output (Target Language) 3")
 ]
 def update_outputs(image, file, audio, text, input_language, target_language):
     final_text, top_phrases, translations, audio_outputs = process_input(