Update app.py

app.py

@@ -43,12 +43,22 @@ def speech_to_text(audio_sample):
   #text = audio_sample["text"].lower()
   #print(text)
   #speech_data = audio_sample["audio"]["array"]
-  print("————————")
-  print(audio_sample)
-  print(audio_sample[1])
-  print("————————")
+  
+  print(f"""
+  ————————
+  audio sample: {audio_sample}
+  audio array: {audio_sample[1]}
+  ————————
+  """)
+  
   output = diffuser_pipeline(audio_sample[1])
   
+  print(f"""
+  ————————
+  output: {output}
+  ————————
+  """)
+  
   return output.images[0]
 
 demo = gr.Interface(fn=speech_to_text, inputs=audio_input, outputs=image_output, title=title, description=description)