Update app.py

app.py

@@ -80,7 +80,7 @@ def example_inference(input_text, count, image, img_qn, audio):
     pred_text = textMode(input_text, count)
     pred_text_image = imageMode(image, img_qn)
     pred_text_audio = audioMode(audio)
-    return pred_text #, "in progress", "in progress"
+    return pred_text, pred_text_image, pred_text_audio
 
 
 
@@ -174,7 +174,7 @@ with gr.Blocks() as demo:
             ["What is a large language model?","50","zebras.png","Are the zebras walking or standing still in the image?","WtIsML.m4a"]            
         ],
         inputs=[text_input, text_input_count], #, image_input, image_text_input, audio_input],
-        outputs=[text_output], #, image_text_output, audio_text_output],
+        outputs=[text_output, image_text_output, audio_text_output],
         fn=example_inference,
     )