Update app.py

app.py

@@ -42,14 +42,16 @@ def caption_my_image(pil_image):
 
     semantics = caption_image(images=pil_image)[0]['generated_text']
     audio = generate_audio(semantics)
-    return audio
+    return semantics,audio
 
 
 gr.close_all()
 
 demo = gr.Interface(fn=caption_my_image,
                     inputs=[gr.Image(label="Select Image",type="pil")],
-                    outputs=[ gr.Audio(label="Image Caption")],
+                    outputs=[ 
+                        gr.Textbox(label="Image Caption"),
+                        gr.Audio(label="Image Caption Audio")],
                     title="IMAGE CAPTIONING WITH AUDIO OUTPUT",
                     description="THIS APPLICATION WILL BE USED TO CAPTION IMAGES WITH THE HELP OF AI")
 demo.launch()