Update app.py

app.py

@@ -14,12 +14,12 @@ def predict(prompt):
     wav = wav_bytes_from_spectrogram_image(spec)
     with open("output.wav", "wb") as f:
         f.write(wav[0].getbuffer())
-    return spec, 'output.wav'
+    return 'output.wav'
 
 gr.Interface(
     predict,
     inputs="text",
-    outputs=[gr.Image(), gr.Audio(type='filepath')],
+    outputs=[gr.Audio(type='filepath')],
     title="Riffusion Text-to-Music",
     description="Describe a musical prompt, generate music by getting a Riffusion spectrogram and its corresponding sound"
 ).queue(max_size=32, concurrency_count=20).launch(debug=True)