Update app.py

app.py

@@ -9,13 +9,16 @@ import numpy as np
 import openai
 from llama_index import GPTVectorStoreIndex, SimpleDirectoryReader, Prompt
 from transformers import pipeline
+import opencc
 
+converter = opencc.OpenCC('t2s')  # 创建一个OpenCC实例，指定繁体字转为简体字
 ocr = CnOcr()  # 初始化ocr模型
 history_max_len = 500  # 机器人记忆的最大长度
 all_max_len = 2000  # 输入的最大长度
 asr_model_id = "openai/whisper-tiny"  # 更新为你的模型ID
 asr_pipe = pipeline("automatic-speech-recognition", model=asr_model_id)
 
+
 def get_text_emb(open_ai_key, text):  # 文本向量化
     openai.api_key = open_ai_key  # 设置openai的key
     response = openai.Embedding.create(
@@ -196,7 +199,9 @@ def transcribe_speech(filepath):
         chunk_length_s=30,
         batch_size=8,
     )
-    return output["text"]
+    # 转换为简体字
+    simplified_text = converter.convert(output["text"])
+    return simplified_text
 
 
 with gr.Blocks() as demo: