Update app.py

app.py

@@ -84,23 +84,16 @@ def process_audio_text(text, audio):
     # 处理音频输入
     audio_path = process_audio_input(audio)
     
-    # 检查是否有输入
-    if not text and not audio_path:
-        yield "Please provide either text or audio input.", None
-        return
-
-    # 构建对话输入
-    conversation = {
-        "from": "user",
-        "value": text if text else ""
-    }
+    text = ""
     
-    # 如果有音频，添加到对话中
-    if audio_path:
-        conversation["audio"] = audio_path
-
     tmp = [{
-        "conversations": [conversation]
+        "conversations": [
+            {
+                "from": "user",
+                "value": text,
+                "audio": audio_path
+            }
+        ]
     }]
     
     accumulated_text = ""
@@ -130,14 +123,14 @@ 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.Textbox(label="Enter text instruction", value=""),
             gr.Audio(type="filepath", label="Upload Audio")
         ],
         outputs=[
@@ -149,4 +142,4 @@ if __name__ == "__main__":
         allow_flagging="never"
     )
 
-    iface.launch(server_name="0.0.0.0", server_port=7860)
+    iface.launch(server_name="0.0.0.0", server_port=7860, share=False)