Update app.py

app.py

@@ -34,7 +34,8 @@ def infer(image_input, manual_caption, duration_in, seed, caption_output):
         print("manual caption: " + cap)
         ph_update=""
     
-    sound = audio_gen(cap, duration_in, 2.5, seed, 3, fn_index=0)
+    sound = audio_gen(cap, duration_in, 2.5, seed, 3, "audioldm-m-text-ft", fn_index=0)
+
     print(sound)