Update app.py

app.py

@@ -51,7 +51,7 @@ def input_changes(input_vid):
         caps = []
         for one_frame in picked_frames:
             cap = caption(one_frame, "Beam search", 1.2, 0.5, 5, 20, fn_index=0)
-            caps.append(cap)
+            caps.append(f"the sound of {cap}")
             print(caps)
         final_cap = '\n then '.join(caps)
         print(final_cap)