Update app.py

app.py

@@ -12,11 +12,13 @@ def get_pipeline_prediction(pil_image):
     pipeline_output = od_pipe(pil_image)
     text = summarize_predictions_natural_language(pipeline_output)
     #text = "Hello, my name is Ratha"
-    gen_audio = tts_pipe(text)
+    
     processed_image = render_results_in_image(pil_image,
                                             pipeline_output)
+    gen_audio = tts_pipe(text)
     rate= gen_audio["sampling_rate"]
-    return processed_image, text, (rate, gen_audio["audio"][0])
+    return processed_image, text
+            #, (rate, gen_audio["audio"][0])
 
 demo = gr.Interface(
   fn=get_pipeline_prediction,
@@ -24,8 +26,9 @@ demo = gr.Interface(
                   type="pil"),
   outputs= [
           gr.Image(label="Output image with predicted instances", type="pil"),
-          gr.Textbox(label="Prediction Summary"),
-          gr.Audio(label="Generated Speech")]
+          gr.Textbox(label="Prediction Summary")
+          #,gr.Audio(label="Generated Speech")
+      ]
 )
 
 demo.launch()