changed modelscope widgets to gradio widgets

demo/web_demo_audio.py

@@ -115,26 +115,53 @@ def _launch_demo(args):
     Qwen2-Audio-Instruct <a href="https://modelscope.cn/models/qwen/Qwen2-Audio-7B-Instruct">🤖 </a> | 
     <a href="https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct">🤗</a>&nbsp ｜ 
     &nbsp<a href="https://github.com/QwenLM/Qwen2-Audio">Github</a></center>""")
-        chatbot = mgr.Chatbot(label='Qwen2-Audio-7B-Instruct', elem_classes="control-height", height=750)
-
-        user_input = mgr.MultimodalInput(
-            interactive=True,
-            sources=['microphone', 'upload'],
-            submit_button_props=dict(value="🚀 Submit (发送)"),
-            upload_button_props=dict(value="📁 Upload (上传文件)", show_progress=True),
-        )
-        task_history = gr.State([])
+        chatbot = gr.Chatbot(label='Qwen2-Audio-7B-Instruct', height=750)
+        
+        with gr.Row():
+            text_input = gr.Textbox(
+                show_label=False,
+                placeholder="Type your message here...",
+                container=False
+            )
+            audio_input = gr.Audio(
+                sources=["microphone", "upload"],
+                type="filepath"
+            )
 
         with gr.Row():
-            empty_bin = gr.Button("🧹 Clear History (清除历史)")
+            submit_btn = gr.Button("🚀 Submit (发送)")
+            empty_btn = gr.Button("🧹 Clear History (清除历史)")
             regen_btn = gr.Button("🤔️ Regenerate (重试)")
 
-        user_input.submit(fn=add_text,
-                          inputs=[chatbot, task_history, user_input],
-                          outputs=[chatbot, task_history, user_input]).then(
-            predict, [chatbot, task_history], [chatbot, task_history], show_progress=True
+        task_history = gr.State([])
+
+        # Update event handlers for new input components
+        def process_input(text, audio, chatbot, history):
+            content = []
+            if audio is not None:
+                content.append({'type': 'audio', 'audio_url': audio})
+            if text:
+                content.append({'type': 'text', 'text': text})
+            
+            history.append({"role": "user", "content": content})
+            chatbot.append([
+                {"text": text, "audio": audio},
+                None
+            ])
+            return "", None, chatbot, history
+
+        submit_btn.click(
+            fn=process_input,
+            inputs=[text_input, audio_input, chatbot, task_history],
+            outputs=[text_input, audio_input, chatbot, task_history]
+        ).then(
+            predict,
+            [chatbot, task_history],
+            [chatbot, task_history],
+            show_progress=True
         )
-        empty_bin.click(reset_state, outputs=[chatbot, task_history], show_progress=True)
+
+        empty_btn.click(reset_state, outputs=[chatbot, task_history], show_progress=True)
         regen_btn.click(regenerate, [chatbot, task_history], [chatbot, task_history], show_progress=True)
 
     demo.queue().launch(