默认OpenAI的 语音识别报错

[gamilwcy]

trafficstars

环境: Docker 部署，openai官方api链接 docker中 python: 3.10.13 使用场景：个人微信

docker-compose.yml配置如下

services:
  chatgpt-on-wechat:
    image: zhayujie/chatgpt-on-wechat
    container_name: chatgpt-on-wechat
    security_opt:
      - seccomp:unconfined
    environment:
      OPEN_AI_API_KEY: 'sk-xxxx'
      MODEL: 'gpt-3.5-turbo'
      PROXY: ''
      SINGLE_CHAT_PREFIX: '[""]'
      SINGLE_CHAT_REPLY_PREFIX: '""'
      GROUP_CHAT_PREFIX: '["@bot"]'
      GROUP_NAME_WHITE_LIST: '[""]'
      IMAGE_CREATE_PREFIX: '["画", "看", "找"]'
      CONVERSATION_MAX_TOKENS: 1000
      SPEECH_RECOGNITION: 'True'
      CHARACTER_DESC: '你是公司客服, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流>。'
      EXPIRES_IN_SECONDS: 3600
      USE_GLOBAL_PLUGIN_CONFIG: 'True'
      USE_LINKAI: 'False'
      LINKAI_API_KEY: ''
      LINKAI_APP_CODE: ''
      VOICE_TO_TEXT: "openai"
      TEXT_TO_VOICE: "openai"
      VOICE_REPLY_VOICE: "true"
      VOICE_TO_TEXT: "true"
      TEXT_TO_VOICE_MODEL: "tts-1"
      TTS_VOICE_ID: "alloy"
      CHANNEL_TYPE: "wx"

现象：文字可以正常回复，语音后台打印直接报错

[INFO][2023-12-21 07:43:59][bridge.py:49] - create bot chatGPT for chat
[INFO][2023-12-21 07:43:59][chat_gpt_bot.py:49] - [CHATGPT] query=你好
[INFO][2023-12-21 07:44:04][wechat_channel.py:191] - [WX] sendMsg=Reply(type=TEXT, content=你好！有什么问题我可以帮助你解决吗？), receiver=@2c5b07608af3fe0ce096b263082071cf
[INFO][2023-12-21 07:44:26][bridge.py:49] - create bot True for voice_to_text
[ERROR][2023-12-21 07:44:26][chat_channel.py:299] - Worker return exception:
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
  File "/app/channel/chat_channel.py", line 168, in _handle
    reply = self._generate_reply(context)
  File "/app/channel/chat_channel.py", line 201, in _generate_reply
    reply = super().build_voice_to_text(wav_path)
  File "/app/channel/channel.py", line 40, in build_voice_to_text
    return Bridge().fetch_voice_to_text(voice_file)
  File "/app/bridge/bridge.py", line 67, in fetch_voice_to_text
    return self.get_bot("voice_to_text").voiceToText(voiceFile)
  File "/app/bridge/bridge.py", line 53, in get_bot
    self.bots[typename] = create_voice(self.btype[typename])
  File "/app/voice/factory.py", line 45, in create_voice
    raise RuntimeError
RuntimeError

[wangluyichen]

没人能完全解决这个问题，只能靠作者。。。

[6vision]

最新版本已修复，可更新代码