Update app.py

app.py

@@ -1,3 +1,5 @@
+import spaces
+
 import os
 import streamlit as st
 from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
@@ -5,7 +7,6 @@ import soundfile as sf
 import numpy as np
 import torch  # Import torch
 from espnet2.bin.tts_inference import Text2Speech
-import spaces
 
 # --- Whisper (ASR) - We'll use this instead of image captioning ---
 ASR_MODEL_NAME = "openai/whisper-large-v2"