Update app.py

app.py

@@ -52,9 +52,13 @@ def _load_model_tokenizer():
     tokenizer = AutoTokenizer.from_pretrained(model_id,  trust_remote_code=True)
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto",trust_remote_code=True, fp16=True).eval()  
     return model, tokenizer
-whisper_model = load_whisper()
-tts_model, tokenizer_tss = load_tts()
-model, tokenizer = _load_model_tokenizer()
+
+if torch.cuda.is_available():
+    whisper_model = load_whisper()
+    tts_model, tokenizer_tss = load_tts()
+    model, tokenizer = _load_model_tokenizer()
+
+
 def postprocess(self, y):
     if y is None:
         return []
@@ -96,7 +100,7 @@ def _parse_text(text):
                 lines[i] = "<br>" + line
     text = "".join(lines)
     return text
-
+@spaces.GPU
 def predict(_query, _chatbot, _task_history):
     print(f"User: {_parse_text(_query)}")
     _chatbot.append((_parse_text(_query), ""))