diff --git a/.gitignore b/.gitignore index c4d7bdc..8bc62f3 100644 --- a/.gitignore +++ b/.gitignore @@ -6,3 +6,4 @@ venv* config.json QR.png nohup.out +tmp diff --git a/README.md b/README.md index c3c2682..5427fbb 100644 --- a/README.md +++ b/README.md @@ -71,6 +71,14 @@ cd chatgpt-on-wechat/ ```bash pip3 install itchat-uos==1.5.0.dev0 pip3 install --upgrade openai + +如果使用百度的语音识别，需要安装百度的pythonSDK +pip3 install baidu-aip chardet +如果使用google的语音识别，需要安装speech_recognition和依赖的ffmpeg和espeak +pip3 install SpeechRecognition +--在MacOS中安装ffmpeg，brew install ffmpeg espeak +--在Windows中安装ffmpeg，下载ffmpeg.exe +--在Linux中安装ffmpeg，apt-get install ffmpeg espeak ``` 注：`itchat-uos`使用指定版本1.5.0.dev0，`openai`使用最新版本，需高于0.27.0。 @@ -112,7 +120,11 @@ cp config-template.json config.json + 默认只要被人 @ 就会触发机器人自动回复；另外群聊天中只要检测到以 "@bot" 开头的内容，同样会自动回复（方便自己触发），这对应配置项 `group_chat_prefix` + 可选配置: `group_name_keyword_white_list`配置项支持模糊匹配群名称，`group_chat_keyword`配置项则支持模糊匹配群消息内容，用法与上述两个配置项相同。（Contributed by [evolay](https://github.com/evolay)) -**3.其他配置** +**3.语音识别** ++ 配置`speech_recognition=true`开启语音识别，默认使用openai的whisper模型 ++ 配置`voice_reply_voice=true`语音回复语音，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。使用wechaty则回复的是微信语音。 + +**4.其他配置** + `proxy`：由于目前 `openai` 接口国内无法访问，需配置代理客户端的地址，详情参考 [#351](https://github.com/zhayujie/chatgpt-on-wechat/issues/351) + 对于图像生成，在满足个人或群组触发条件外，还需要额外的关键词前缀来触发，对应配置 `image_create_prefix ` diff --git a/bridge/bridge.py b/bridge/bridge.py index 6c164e8..e739a7f 100644 --- a/bridge/bridge.py +++ b/bridge/bridge.py @@ -1,4 +1,5 @@ from bot import bot_factory +from voice import voice_factory class Bridge(object): @@ -7,3 +8,9 @@ class Bridge(object): def fetch_reply_content(self, query, context): return bot_factory.create_bot("chatGPT").reply(query, context) + + def fetch_voice_to_text(self, voiceFile): + return voice_factory.create_voice("openai").voiceToText(voiceFile) + + def fetch_text_to_voice(self, text): + return voice_factory.create_voice("baidu").textToVoice(text) \ No newline at end of file diff --git a/channel/channel.py b/channel/channel.py index e2617d1..a1395c4 100644 --- a/channel/channel.py +++ b/channel/channel.py @@ -11,7 +11,7 @@ class Channel(object): """ raise NotImplementedError - def handle(self, msg): + def handle_text(self, msg): """ process received msg :param msg: message object @@ -29,3 +29,9 @@ class Channel(object): def build_reply_content(self, query, context=None): return Bridge().fetch_reply_content(query, context) + + def build_voice_to_text(self, voice_file): + return Bridge().fetch_voice_to_text(voice_file) + + def build_text_to_voice(self, text): + return Bridge().fetch_text_to_voice(text) diff --git a/channel/wechat/wechat_channel.py b/channel/wechat/wechat_channel.py index 66778f4..b861e35 100644 --- a/channel/wechat/wechat_channel.py +++ b/channel/wechat/wechat_channel.py @@ -3,12 +3,14 @@ """ wechat channel """ + import itchat import json from itchat.content import * from channel.channel import Channel from concurrent.futures import ThreadPoolExecutor from common.log import logger +from common.tmp_dir import TmpDir from config import conf import requests import io @@ -18,7 +20,7 @@ thread_pool = ThreadPoolExecutor(max_workers=8) @itchat.msg_register(TEXT) def handler_single_msg(msg): - WechatChannel().handle(msg) + WechatChannel().handle_text(msg) return None @@ -28,6 +30,12 @@ def handler_group_msg(msg): return None +@itchat.msg_register(VOICE) +def handler_single_voice(msg): + WechatChannel().handle_voice(msg) + return None + + class WechatChannel(Channel): def __init__(self): pass @@ -39,12 +47,27 @@ class WechatChannel(Channel): # start message listener itchat.run() - def handle(self, msg): - logger.debug("[WX]receive msg: " + json.dumps(msg, ensure_ascii=False)) + def handle_voice(self, msg): + if conf().get('speech_recognition') != True : + return + logger.debug("[WX]receive voice msg: " + msg['FileName']) + thread_pool.submit(self._do_handle_voice, msg) + + def _do_handle_voice(self, msg): + fileName = TmpDir().path() + msg['FileName'] + msg.download(fileName) + content = super().build_voice_to_text(fileName) + self._handle_single_msg(msg, content, conf().get('voice_reply_voice')) + + def handle_text(self, msg): + logger.debug("[WX]receive text msg: " + json.dumps(msg, ensure_ascii=False)) + content = msg['Text'] + self._handle_single_msg(msg, content, False) + + def _handle_single_msg(self, msg, content, reply_voice=False): from_user_id = msg['FromUserName'] to_user_id = msg['ToUserName'] # 接收人id other_user_id = msg['User']['UserName'] # 对手方id - content = msg['Text'] match_prefix = self.check_prefix(content, conf().get('single_chat_prefix')) if "」\n- - - - - - - - - - - - - - -" in content: logger.debug("[WX]reference query skipped") @@ -60,9 +83,10 @@ class WechatChannel(Channel): if img_match_prefix: content = content.split(img_match_prefix, 1)[1].strip() thread_pool.submit(self._do_send_img, content, from_user_id) - else: - thread_pool.submit(self._do_send, content, from_user_id) - + elif reply_voice: + thread_pool.submit(self._do_send_voice, content, from_user_id) + else : + thread_pool.submit(self._do_send_text, content, from_user_id) elif to_user_id == other_user_id and match_prefix: # 自己给好友发送消息 str_list = content.split(match_prefix, 1) @@ -72,8 +96,10 @@ class WechatChannel(Channel): if img_match_prefix: content = content.split(img_match_prefix, 1)[1].strip() thread_pool.submit(self._do_send_img, content, to_user_id) + elif reply_voice: + thread_pool.submit(self._do_send_voice, content, to_user_id) else: - thread_pool.submit(self._do_send, content, to_user_id) + thread_pool.submit(self._do_send_text, content, to_user_id) def handle_group(self, msg): @@ -105,10 +131,24 @@ class WechatChannel(Channel): thread_pool.submit(self._do_send_group, content, msg) def send(self, msg, receiver): - logger.info('[WX] sendMsg={}, receiver={}'.format(msg, receiver)) itchat.send(msg, toUserName=receiver) + logger.info('[WX] sendMsg={}, receiver={}'.format(msg, receiver)) - def _do_send(self, query, reply_user_id): + def _do_send_voice(self, query, reply_user_id): + try: + if not query: + return + context = dict() + context['from_user_id'] = reply_user_id + reply_text = super().build_reply_content(query, context) + if reply_text: + replyFile = super().build_text_to_voice(reply_text) + itchat.send_file(replyFile, toUserName=reply_user_id) + logger.info('[WX] sendFile={}, receiver={}'.format(replyFile, reply_user_id)) + except Exception as e: + logger.exception(e) + + def _do_send_text(self, query, reply_user_id): try: if not query: return @@ -138,8 +178,8 @@ class WechatChannel(Channel): image_storage.seek(0) # 图片发送 - logger.info('[WX] sendImage, receiver={}'.format(reply_user_id)) itchat.send_image(image_storage, reply_user_id) + logger.info('[WX] sendImage, receiver={}'.format(reply_user_id)) except Exception as e: logger.exception(e) diff --git a/common/tmp_dir.py b/common/tmp_dir.py new file mode 100644 index 0000000..1738022 --- /dev/null +++ b/common/tmp_dir.py @@ -0,0 +1,20 @@ + +import os +import pathlib +from config import conf + + +class TmpDir(object): + """A temporary directory that is deleted when the object is destroyed. + """ + + tmpFilePath = pathlib.Path('./tmp/') + + def __init__(self): + pathExists = os.path.exists(self.tmpFilePath) + if not pathExists and conf().get('speech_recognition') == True: + os.makedirs(self.tmpFilePath) + + def path(self): + return str(self.tmpFilePath) + '/' + \ No newline at end of file diff --git a/config-template.json b/config-template.json index fd6d46a..7e693f6 100644 --- a/config-template.json +++ b/config-template.json @@ -7,6 +7,11 @@ "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"], "image_create_prefix": ["画", "看", "找"], "conversation_max_tokens": 1000, + "speech_recognition": false, + "voice_reply_voice": false, + "baidu_app_id": "YOUR BAIDU APP ID", + "baidu_api_key": "YOUR BAIDU API KEY", + "baidu_secret_key": "YOUR BAIDU SERVICE KEY", "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。", "expires_in_seconds": 3600 } diff --git a/voice/baidu/baidu_voice.py b/voice/baidu/baidu_voice.py new file mode 100644 index 0000000..d99db37 --- /dev/null +++ b/voice/baidu/baidu_voice.py @@ -0,0 +1,36 @@ + +""" +baidu voice service +""" +import time +from aip import AipSpeech +from common.log import logger +from common.tmp_dir import TmpDir +from voice.voice import Voice +from config import conf + +class BaiduVoice(Voice): + APP_ID = conf().get('baidu_app_id') + API_KEY = conf().get('baidu_api_key') + SECRET_KEY = conf().get('baidu_secret_key') + client = AipSpeech(APP_ID, API_KEY, SECRET_KEY) + + def __init__(self): + pass + + def voiceToText(self, voice_file): + pass + + def textToVoice(self, text): + result = self.client.synthesis(text, 'zh', 1, { + 'spd': 5, 'pit': 5, 'vol': 5, 'per': 111 + }) + if not isinstance(result, dict): + fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3' + with open(fileName, 'wb') as f: + f.write(result) + logger.info('[Baidu] textToVoice text={} voice file name={}'.format(text, fileName)) + return fileName + else: + logger.error('[Baidu] textToVoice error={}'.format(result)) + return None diff --git a/voice/google/google_voice.py b/voice/google/google_voice.py new file mode 100644 index 0000000..8e339f2 --- /dev/null +++ b/voice/google/google_voice.py @@ -0,0 +1,51 @@ + +""" +google voice service +""" + +import pathlib +import subprocess +import time +import speech_recognition +import pyttsx3 +from common.log import logger +from common.tmp_dir import TmpDir +from voice.voice import Voice + + +class GoogleVoice(Voice): + recognizer = speech_recognition.Recognizer() + engine = pyttsx3.init() + + def __init__(self): + # 语速 + self.engine.setProperty('rate', 125) + # 音量 + self.engine.setProperty('volume', 1.0) + # 0为男声，1为女声 + voices = self.engine.getProperty('voices') + self.engine.setProperty('voice', voices[1].id) + + def voiceToText(self, voice_file): + new_file = voice_file.replace('.mp3', '.wav') + subprocess.call('ffmpeg -i ' + voice_file + + ' -acodec pcm_s16le -ac 1 -ar 16000 ' + new_file, shell=True) + with speech_recognition.AudioFile(new_file) as source: + audio = self.recognizer.record(source) + try: + text = self.recognizer.recognize_google(audio, language='zh-CN') + logger.info( + '[Google] voiceToText text={} voice file name={}'.format(text, voice_file)) + return text + except speech_recognition.UnknownValueError: + return "抱歉，我听不懂。" + except speech_recognition.RequestError as e: + return "抱歉，无法连接到 Google 语音识别服务；{0}".format(e) + + def textToVoice(self, text): + textFile = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3' + self.engine.save_to_file(text, textFile) + self.engine.runAndWait() + logger.info( + '[Google] textToVoice text={} voice file name={}'.format(text, textFile)) + return textFile diff --git a/voice/openai/openai_voice.py b/voice/openai/openai_voice.py new file mode 100644 index 0000000..475aac6 --- /dev/null +++ b/voice/openai/openai_voice.py @@ -0,0 +1,27 @@ + +""" +google voice service +""" +import json +import openai +from config import conf +from common.log import logger +from voice.voice import Voice + + +class OpenaiVoice(Voice): + def __init__(self): + openai.api_key = conf().get('open_ai_api_key') + + def voiceToText(self, voice_file): + logger.debug( + '[Openai] voice file name={}'.format(voice_file)) + file = open(voice_file, "rb") + reply = openai.Audio.transcribe("whisper-1", file) + text = reply["text"] + logger.info( + '[Openai] voiceToText text={} voice file name={}'.format(text, voice_file)) + return text + + def textToVoice(self, text): + pass diff --git a/voice/voice.py b/voice/voice.py new file mode 100644 index 0000000..52d8aaa --- /dev/null +++ b/voice/voice.py @@ -0,0 +1,16 @@ +""" +Voice service abstract class +""" + +class Voice(object): + def voiceToText(self, voice_file): + """ + Send voice to voice service and get text + """ + raise NotImplementedError + + def textToVoice(self, text): + """ + Send text to voice service and get voice + """ + raise NotImplementedError \ No newline at end of file diff --git a/voice/voice_factory.py b/voice/voice_factory.py new file mode 100644 index 0000000..053840e --- /dev/null +++ b/voice/voice_factory.py @@ -0,0 +1,20 @@ +""" +voice factory +""" + +def create_voice(voice_type): + """ + create a voice instance + :param voice_type: voice type code + :return: voice instance + """ + if voice_type == 'baidu': + from voice.baidu.baidu_voice import BaiduVoice + return BaiduVoice() + elif voice_type == 'google': + from voice.google.google_voice import GoogleVoice + return GoogleVoice() + elif voice_type == 'openai': + from voice.openai.openai_voice import OpenaiVoice + return OpenaiVoice() + raise RuntimeError