Update app.py

app.py

@@ -58,7 +58,7 @@ def process_audio_input(audio):
         return None
 
 @spaces.GPU(duration=180)  # 使用ZeroGPU，3分钟超时
-def process_audio_text(text, audio):
+def process_audio_text(audio):
     """主要处理函数"""
     global _MODEL_ON_CUDA, inference_model
     
@@ -123,23 +123,20 @@ init_model()
 
 if __name__ == "__main__":
     examples = [
-        ["", "./show_case/1.wav"],
-        ["", "./show_case/2.wav"],
+        ["./show_case/1.wav"],
+        ["./show_case/2.wav"],
     ]  
 
     iface = gr.Interface(
         fn=process_audio_text,
         inputs=[
-            gr.Textbox(label="Enter text instruction", value=""),
             gr.Audio(type="filepath", label="Upload Audio")
         ],
         outputs=[
-            gr.Textbox(label="Model output"),
-            gr.Audio(label="Streamed Audio", streaming=True, autoplay=True)
+            gr.Audio(label="Streamed Audio", streaming=True, autoplay=True),
+            gr.Textbox(label="Model output")
         ],
         examples=examples,
-        title="🔊 EchoX Assistant",
-        description="A multimodal AI assistant that understands speech and responds with both text and audio",
         live=False,
         allow_flagging="never"
     )