adding labels to outputs

app.py

@@ -70,9 +70,10 @@ model_selection_input = gr.Radio(["Basic Model",
                                   "ViT-GPT2"],
                                  label="Choose Model")
 
+
 iface = gr.Interface(fn=process_image_and_generate_output,
                      inputs=[image_input, model_selection_input],
-                     outputs=["text", "audio"],
+                     outputs=[gr.Text(label="Caption"),gr.Audio(label="Audio")],
                      examples=sample_images,
                      allow_flagging='never',
                      title="Eye For Blind | Image Captioning & TTS Demo",