Update app.py

app.py

@@ -21,7 +21,7 @@ diffuser_pipeline = DiffusionPipeline.from_pretrained(
     speech_processor=processor,
     use_auth_token=MY_SECRET_TOKEN,
     revision="fp16",
-    torch_dtype=torch.float16,
+    #torch_dtype=torch.float16,
 )
 
 diffuser_pipeline.enable_attention_slicing()
@@ -34,10 +34,10 @@ audio_input = gr.Audio(source="microphone")
 image_output = gr.Image()
 
 def speech_to_text(audio_sample):
-  text = audio_sample["text"].lower()
-  print(text)
-  speech_data = audio_sample["audio"]["array"]
-  output = diffuser_pipeline(speech_data)
+  #text = audio_sample["text"].lower()
+  #print(text)
+  #speech_data = audio_sample["audio"]["array"]
+  output = diffuser_pipeline(audio_sample)
   
   return output.images[0]