Update app.py

app.py

@@ -49,7 +49,7 @@ def generate_response(transcription):
             {"role": "user", "content": transcription},
         ]
         tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
-        input_ids = tokenized_chat[0].to('cuda')
+        input_ids = tokenized_chat[0].to('device')
         if len(input_ids.shape) == 1:
             input_ids = input_ids.unsqueeze(0)
         with torch.no_grad():