recognize_google报WinError10054：VPN适配、原因及替代方案咨询

问题场景 #

运行网上找到的语音转文字示例时，仅在开启VPN连接时，recognize_google函数执行失败，报错如下：

the surrounding noise level
listens for the user's input
Using google to recognize audio
Traceback (most recent call last):
  File "C:\Users\pvpkumar\PycharmProjects\AI_Jedai\aud_inp_reco.py", line 41, in <module>
    MyText = r.recognize_google(audio2)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\site-packages\speech_recognition\_init_.py", line 840, in recognize_google
    response = urlopen(request, timeout=self.operation_timeout)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\urllib\request.py", line 216, in urlopen
    return opener.open(url, data, timeout)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\urllib\request.py", line 519, in open
    response = self._open(req, data)
               ^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\urllib\request.py", line 536, in _open
    result = self._call_chain(self.handle_open, protocol, protocol +
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\urllib\request.py", line 496, in _call_chain
    result = func(*args)
             ^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\urllib\request.py", line 1377, in http_open
    return self.do_open(http.client.HTTPConnection, req)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\urllib\request.py", line 1352, in do_open
    r = h.getresponse()
        ^^^^^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\http\client.py", line 1374, in getresponse
    response.begin()
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\http\client.py", line 318, in begin
    version, status, reason = self._read_status()
                              ^^^^^^^^^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\http\client.py", line 279, in _read_status
    line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\pvpkumar\AppData\Local\Programs\Python\Python311\Lib\socket.py", line 706, in readinto
    return self._sock.recv_into(b)
           ^^^^^^^^^^^^^^^^^^^^^^^
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host

Process finished with exit code 1

对应的运行代码：

import speech_recognition as sr
import pyttsx3

# Initialize the recognizer
r = sr.Recognizer()


# Function to convert text to
# speech
def SpeakText(command):
    # Initialize the engine
    engine = pyttsx3.init()
    engine.say(command)
    engine.runAndWait()


# Loop infinitely for user to
# speak

while (1):

    # Exception handling to handle
    # exceptions at the runtime
    try:

        # use the microphone as source for input.
        with sr.Microphone() as source2:

            # wait for a second to let the recognizer
            # adjust the energy threshold based on
            # the surrounding noise level
            print("the surrounding noise level")
            r.adjust_for_ambient_noise(source2, duration=0.2)

            # listens for the user's input
            print("listens for the user's input")
            audio2 = r.listen(source2)

            # Using google to recognize audio
            print("Using google to recognize audio")
            MyText = r.recognize_google(audio2)
            MyText = MyText.lower()

            print("Did you say ", MyText)
            SpeakText(MyText)

    except sr.RequestError as e:
        print("Could not request results; {0}".format(e))

    except sr.UnknownValueError:
        print("unknown error occurred")

1. 故障原因 #

• VPN节点IP被Google拦截：部分VPN共享节点IP因频繁请求、违反使用策略，被Google的反访问限制机制判定为异常，强行关闭连接。
• VPN链路不稳定：VPN节点与Google服务器间的网络出现丢包、延迟过高，导致TCP传输音频数据时被远程端强制终止连接。
• VPN流量过滤冲突：部分VPN会对HTTPS请求做中间人拦截或修改请求头，导致Google服务器无法识别合法请求，主动断开连接。

2. recognize_google的可用替代方案 #

• recognize_google_cloud：使用Google Cloud官方语音识别API，需申请API密钥，稳定性和准确率更高，支持多语言与自定义模型，替换代码调用方法并传入密钥即可。
• recognize_wit：调用Wit.ai语音识别服务，需注册获取API密钥，支持多语言，适合轻量级应用。
• recognize_sphinx：CMU Sphinx本地识别引擎，无需联网，适合离线场景，但准确率低于在线服务，中文支持有限。
• recognize_azure：微软Azure语音服务，提供免费额度，支持多语言与实时识别，需申请Azure账号和密钥。

3. VPN设置调整建议 #

• 切换VPN节点：优先选择正规商用的欧美地区节点，避免使用免费/共享IP的节点，降低被Google拦截的概率。
• 启用流量白名单：将speech.googleapis.com、www.google.com等Google语音识别相关域名加入VPN白名单，让这类流量不经过VPN，直接走本地网络。
• 关闭HTTPS拦截：若VPN开启了SSL/TLS中间人拦截功能，需关闭该选项，避免Google服务器验证请求失败。
• 切换传输协议：尝试使用WireGuard、OpenVPN UDP等更稳定的协议，减少网络波动引发的连接重置问题。

内容的提问来源于stack exchange，提问作者Pvp Kumar