Update app.py

app.py

@@ -1,4 +1,11 @@
 import spaces
+import subprocess
+# Install flash attention, skipping CUDA build if necessary
+subprocess.run(
+    "pip install flash-attn --no-build-isolation",
+    env={"FLASH_ATTENTION_SKIP_CUDA_BUILD": "TRUE"},
+    shell=True,
+)
 import argparse, os, sys, glob
 import pathlib
 directory = pathlib.Path(os.getcwd())
@@ -16,7 +23,6 @@ import preprocess.n2s_by_openai as n2s
 from vocoder.bigvgan.models import VocoderBigVGAN
 import soundfile
 import math
-import gradio
 import gradio as gr
 
 def load_model_from_config(config, ckpt = None, verbose=True):