load model only if cuda available

app.py

@@ -123,18 +123,22 @@ def download_whisper_model():
     except Exception as e:
         print(f"An error occurred while downloading the model: {str(e)}")
 
-# Download the Whisper model
-download_whisper_model()
-
-total_vram_in_gb = torch.cuda.get_device_properties(0).total_memory / 1073741824
-print(f'\033[32mCUDA版本：{torch.version.cuda}\033[0m')
-print(f'\033[32mPytorch版本：{torch.__version__}\033[0m')
-print(f'\033[32m显卡型号：{torch.cuda.get_device_name()}\033[0m')
-print(f'\033[32m显存大小：{total_vram_in_gb:.2f}GB\033[0m')
-print(f'\033[32m精度：float16\033[0m')
-dtype = torch.float16
+
 if torch.cuda.is_available():
-        device = "cuda"
+    device = "cuda"
+
+    # Download the Whisper model
+    download_whisper_model()
+
+    total_vram_in_gb = torch.cuda.get_device_properties(0).total_memory / 1073741824
+    print(f'\033[32mCUDA版本：{torch.version.cuda}\033[0m')
+    print(f'\033[32mPytorch版本：{torch.__version__}\033[0m')
+    print(f'\033[32m显卡型号：{torch.cuda.get_device_name()}\033[0m')
+    print(f'\033[32m显存大小：{total_vram_in_gb:.2f}GB\033[0m')
+    print(f'\033[32m精度：float16\033[0m')
+    
+    dtype = torch.float16
+
 else:
     print("cuda not available, using cpu")
     device = "cpu"