diff --git a/README.md b/README.md index aa98432..7f95674 100644 --- a/README.md +++ b/README.md @@ -112,7 +112,7 @@ pip3 install --upgrade tiktoken "image_create_prefix": ["画", "看", "找"], # 开启图片回复的前缀 "conversation_max_tokens": 1000, # 支持上下文记忆的最多字符数 "speech_recognition": false, # 是否开启语音识别 - "group_speech_recognition": false, # 是否开启群组语音识别 (目前仅支持wechaty) + "group_speech_recognition": false, # 是否开启群组语音识别 "use_azure_chatgpt": false, # 是否使用Azure ChatGPT service代替openai ChatGPT service. 当设置为true时需要设置 open_ai_api_base,如 https://xxx.openai.azure.com/ "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 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。", # 人格描述, } @@ -133,8 +133,8 @@ pip3 install --upgrade tiktoken **3.语音识别** -+ 添加 `"speech_recognition": true` 将开启语音识别,默认使用openai的whisper模型识别为文字,同时以文字回复,该参数仅支持私聊 (注意由于语音消息无法匹配前缀,一旦开启将对所有语音自动回复); -+ 添加 `"group_speech_recognition": true` 将开启群组语音识别,默认使用openai的whisper模型识别为文字,同时以文字回复,参数仅支持群聊 (可以匹配group_chat_prefix和group_chat_keyword, 目前wechaty可支持群聊语音触发画图,itchat无法触发画图); ++ 添加 `"speech_recognition": true` 将开启语音识别,默认使用openai的whisper模型识别为文字,同时以文字回复,该参数仅支持私聊 (注意由于语音消息无法匹配前缀,一旦开启将对所有语音自动回复,支持语音触发画图); ++ 添加 `"group_speech_recognition": true` 将开启群组语音识别,默认使用openai的whisper模型识别为文字,同时以文字回复,参数仅支持群聊 (会匹配group_chat_prefix和group_chat_keyword, 支持语音触发画图); + 添加 `"voice_reply_voice": true` 将开启语音回复语音(同时作用于私聊和群聊),但是需要配置对应语音合成平台的key,由于itchat协议的限制,只能发送语音mp3文件,若使用wechaty则回复的是微信语音。 **4.其他配置** diff --git a/app.py b/app.py index c95f39c..7d42b9d 100644 --- a/app.py +++ b/app.py @@ -24,4 +24,4 @@ def run(): logger.exception(e) if __name__ == '__main__': - run() + run() \ No newline at end of file diff --git a/channel/wechat/wechat_channel.py b/channel/wechat/wechat_channel.py index 9fa4821..c7c660d 100644 --- a/channel/wechat/wechat_channel.py +++ b/channel/wechat/wechat_channel.py @@ -190,14 +190,14 @@ class WechatChannel(Channel): thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback) def handle_group_voice(self, msg): - if conf().get('group_speech_recognition') != True: + if conf().get('group_speech_recognition', False) != True: return logger.debug("[WX]receive voice for group msg: " + msg['FileName']) group_name = msg['User'].get('NickName', None) group_id = msg['User'].get('UserName', None) create_time = msg['CreateTime'] # 消息时间 if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60: #跳过1分钟前的历史消息 - logger.debug("[WX]history group message skipped") + logger.debug("[WX]history group voice skipped") return # 验证群名 if not group_name: @@ -260,19 +260,29 @@ class WechatChannel(Channel): file_name = TmpDir().path() + context.content msg.download(file_name) reply = super().build_voice_to_text(file_name) - if reply.type != ReplyType.ERROR and reply.type != ReplyType.INFO: - context.content = reply.content # 语音转文字后,将文字内容作为新的context + if reply.type == ReplyType.TEXT: + content = reply.content # 语音转文字后,将文字内容作为新的context # 如果是群消息,判断是否触发关键字 if context['isgroup']: - match_prefix = check_prefix(context.content, conf().get('group_chat_prefix')) or check_contain(context.content, conf().get('group_chat_keyword')) - if match_prefix != True: + match_prefix = check_prefix(content, conf().get('group_chat_prefix')) + match_contain = check_contain(content, conf().get('group_chat_keyword')) + logger.debug('[WX] group chat prefix match: {}'.format(match_prefix)) + if match_prefix is None and match_contain is None: return - context.type = ContextType.TEXT + else: + if match_prefix: + content = content.replace(match_prefix, '', 1).strip() + + img_match_prefix = check_prefix(content, conf().get('image_create_prefix')) + if img_match_prefix: + content = content.replace(img_match_prefix, '', 1).strip() + context.type = ContextType.IMAGE_CREATE + else: + context.type = ContextType.TEXT + context.content = content reply = super().build_reply_content(context.content, context) if reply.type == ReplyType.TEXT: if conf().get('voice_reply_voice'): - if context['isgroup']: - reply.content = '@' + context['msg']['ActualNickName'] + ' ' + reply.content reply = super().build_text_to_voice(reply.content) else: logger.error('[WX] unknown context type: {}'.format(context.type))