Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 import subprocess
+import spaces
 # Install flash attention, skipping CUDA build if necessary
 subprocess.run(
     "pip install flash-attn --no-build-isolation",
@@ -23,7 +24,7 @@ import base64
 model = Model()
 model.generate_config.max_new_tokens = 50 * 50 # no more than 20s per turn
 
-
+@spaces.GPU(duration=120)
 def process_json_and_generate_audio(prompt_audio_role0_file, prompt_text_role0, prompt_audio_role1_file, prompt_text_role1, json_dialogue_input_str):
     try:
         print(json_dialogue_input_str, type(json_dialogue_input_str))