Update app.py

app.py

@@ -50,10 +50,13 @@ def predict(_chatbot, task_history_str, user_input):
     task_history = parse_task_history(task_history_str)
     print("Type of user_input:", type(user_input))
     print("Type of task_history:", type(task_history))
+
     if not isinstance(task_history, list):
         task_history = []
+
     query = user_input if user_input else (task_history[-1][0] if task_history else "")
     print("User: " + _parse_text(query))
+
     if not task_history:
         return _chatbot
     history_cp = copy.deepcopy(task_history)
@@ -79,7 +82,7 @@ def predict(_chatbot, task_history_str, user_input):
     response, history = model.chat(tokenizer, message, history=history)
     ts_pattern = r"<\|\d{1,2}\.\d+\|>"
     all_time_stamps = re.findall(ts_pattern, response)
-    if (len(all_time_stamps) > 0) and (len(all_time_stamps) % 2 ==0) and last_audio:
+    if all_time_stamps and last_audio:
         ts_float = [ float(t.replace("<|","").replace("|>","")) for t in all_time_stamps]
         ts_float_pair = [ts_float[i:i + 2] for i in range(0,len(all_time_stamps),2)]
         # 读取音频文件
@@ -99,9 +102,11 @@ def predict(_chatbot, task_history_str, user_input):
             audio_clip.export(filename, format=format)
             _chatbot[-1] = (_parse_text(query), chat_response)
             _chatbot.append((None, (str(filename),)))
-    if not _chatbot:
-        _chatbot = [("", "")] 
-
+        return str(filename), _chatbot 
+    else:
+        _chatbot.append((query, response))
+        return response, _chatbot  
+    
     print("Predict - End: task_history =", task_history)
     return _chatbot[-1][1], _chatbot