Merge pull request zhayujie#476 from Chiaki-Chan/master

 1.新增wechaty方案的语音识别、语音回复功能；2.更新README；

.gitignore

@@ -1,5 +1,6 @@
 .DS_Store
 .idea
+.wechaty/
 __pycache__/
 venv*
 *.pyc

README.md

@@ -62,29 +62,60 @@
 支持 Linux、MacOS、Windows 系统（可在Linux服务器上长期运行)，同时需安装 `Python`。 
 > 建议Python版本在 3.7.1~3.9.X 之间，3.10及以上版本在 MacOS 可用，其他系统上不确定能否正常运行。
 
-
-1.克隆项目代码：
+**1.克隆项目代码：**
 
 ```bash
 git clone https://github.com/zhayujie/chatgpt-on-wechat
 cd chatgpt-on-wechat/
 ```
 
-2.安装所需核心依赖：
+**2.安装所需核心依赖：**
 
 ```bash
 pip3 install itchat-uos==1.5.0.dev0
 pip3 install --upgrade openai
 ```
 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。
 
+**3.安装所需拓展依赖（接收语音，回复语音）：**
+### wechaty 处理语音所需
+
+```bash
+pip3 install pysilk
+pip3 install pysilk-mod
+pip3 install pydub
+```
+
+### 百度
+
+```bash
+  pip3 install baidu-aip chardet
+```
+### Google
+
+(1) 安装 SpeechRecognition
+```bash
+  pip3 install SpeechRecognition
+```
+(2) 安装 ffmpeg 和 espeak
+
+  MacOS: 
+  ```bash
+    brew install ffmpeg espeak
+  ```
+  Windows:下载ffmpeg.exe
+
+  Linux: 
+  ```bash
+    apt-get install ffmpeg espeak
+  ```
 
 ## 配置
 
 配置文件的模板在根目录的`config-template.json`中，需复制该模板创建最终生效的 `config.json` 文件：
 
 ```bash
-cp config-template.json config.json
+  cp config-template.json config.json
 ```
 
 然后在`config.json`中填入配置，以下是对默认配置的说明，可根据需要进行自定义修改：
@@ -93,14 +124,21 @@ cp config-template.json config.json
 # config.json文件内容示例
 { 
   "open_ai_api_key": "YOUR API KEY",                          # 填入上面创建的 OpenAI API KEY
+  "open_ai_api_base": "https://api.openai.com/v1",            # 自定义 OpenAI API 地址
   "proxy": "127.0.0.1:7890",                                  # 代理客户端的ip和端口
+  "baidu_app_id": "",                                         # 百度AI的App Id
+  "baidu_api_key": "",                                        # 百度AI的API KEY
+  "baidu_secret_key": "",                                     # 百度AI的Secret KEY
+  "wechaty_puppet_service_token":"",                          # wechaty服务token
   "single_chat_prefix": ["bot", "@bot"],                      # 私聊时文本需要包含该前缀才能触发机器人回复
   "single_chat_reply_prefix": "[bot] ",                       # 私聊时自动回复的前缀，用于区分真人
   "group_chat_prefix": ["@bot"],                              # 群聊时包含该前缀则会触发机器人回复
   "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"], # 开启自动回复的群名称列表
   "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
-  "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
+  "speech_recognition": false,                                # 是否开启语音识别
+  "voice_reply_voice": false,                                 # 是否开启语音回复
+  "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
 }
 ```
 **配置说明：**

channel/wechat/wechaty_channel.py

@@ -10,12 +10,16 @@
 import time
 import asyncio
 import requests
+import pysilk
+import wave
+from pydub import AudioSegment
 from typing import Optional, Union
 from wechaty_puppet import MessageType, FileBox, ScanStatus  # type: ignore
 from wechaty import Wechaty, Contact
 from wechaty.user import Message, Room, MiniProgram, UrlLink
 from channel.channel import Channel
 from common.log import logger
+from common.tmp_dir import TmpDir
 from config import conf
 
 
@@ -89,6 +93,48 @@ async def on_message(self, msg: Message):
                     await self._do_send_img(content, to_user_id)
                 else:
                     await self._do_send(content, to_user_id)
+        elif room is None and msg.type() == MessageType.MESSAGE_TYPE_AUDIO:
+            if not msg.is_self(): # 接收语音消息
+                # 下载语音文件
+                voice_file = await msg.to_file_box()
+                silk_file = TmpDir().path() + voice_file.name
+                await voice_file.to_file(silk_file)
+                logger.info("[WX]receive voice file: " + silk_file)
+                # 将文件转成wav格式音频
+                wav_file = silk_file.replace(".slk", ".wav")
+                with open(silk_file, 'rb') as f:
+                    silk_data = f.read()
+                pcm_data = pysilk.decode(silk_data)
+
+                with wave.open(wav_file, 'wb') as wav_data:
+                    wav_data.setnchannels(1)
+                    wav_data.setsampwidth(2)
+                    wav_data.setframerate(24000)
+                    wav_data.writeframes(pcm_data)
+                if os.path.exists(wav_file): 
+                    converter_state = "true" # 转换wav成功
+                else:
+                    converter_state = "false" # 转换wav失败
+                logger.info("[WX]receive voice converter: " + converter_state)
+                # 语音识别为文本
+                query = super().build_voice_to_text(wav_file)
+                # 交验关键字
+                match_prefix = self.check_prefix(query, conf().get('single_chat_prefix'))
+                if match_prefix is not None:
+                    if match_prefix != '':
+                        str_list = query.split(match_prefix, 1)
+                        if len(str_list) == 2:
+                            query = str_list[1].strip()
+                    # 返回消息
+                    if conf().get('voice_reply_voice'):
+                        await self._do_send_voice(query, from_user_id)
+                    else:
+                        await self._do_send(query, from_user_id)
+                else:
+                    logger.info("[WX]receive voice check prefix: " + 'False')
+                # 清除缓存文件
+                os.remove(wav_file)
+                os.remove(silk_file)
         elif room and msg.type() == MessageType.MESSAGE_TYPE_TEXT:
             # 群组&文本消息
             room_id = room.room_id
@@ -135,6 +181,39 @@ async def _do_send(self, query, reply_user_id):
         except Exception as e:
             logger.exception(e)
 
+
+    async def _do_send_voice(self, query, reply_user_id):
+        try:
+            if not query:
+                return
+            context = dict()
+            context['session_id'] = reply_user_id
+            reply_text = super().build_reply_content(query, context)
+            if reply_text:
+                # 转换 mp3 文件为 silk 格式
+                mp3_file = super().build_text_to_voice(reply_text)
+                silk_file = mp3_file.replace(".mp3", ".silk")
+                # Load the MP3 file
+                audio = AudioSegment.from_file(mp3_file, format="mp3")
+                # Convert to WAV format
+                audio = audio.set_frame_rate(24000).set_channels(1)
+                wav_data = audio.raw_data
+                sample_width = audio.sample_width
+                # Encode to SILK format
+                silk_data = pysilk.encode(wav_data, 24000)
+                # Save the silk file
+                with open(silk_file, "wb") as f:
+                    f.write(silk_data)
+                # 发送语音
+                t = int(time.time())
+                file_box = FileBox.from_file(silk_file, name=str(t) + '.silk')
+                await self.send(file_box, reply_user_id)
+                # 清除缓存文件
+                os.remove(mp3_file)
+                os.remove(silk_file)
+        except Exception as e:
+            logger.exception(e)
+
     async def _do_send_img(self, query, reply_user_id):
         try:
             if not query:

config-template.json

@@ -1,13 +1,18 @@
 {
   "open_ai_api_key": "YOUR API KEY",
   "proxy": "",
+  "wechaty_puppet_service_token":"",
+  "baidu_app_id": "",
+  "baidu_api_key": "",
+  "baidu_secret_key": "",
   "single_chat_prefix": ["bot", "@bot"],
   "single_chat_reply_prefix": "[bot] ",
   "group_chat_prefix": ["@bot"],
   "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,
-  "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
+  "voice_reply_voice": false,
+  "conversation_max_tokens": 1000,
+  "expires_in_seconds": 3600,
+  "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。"
 }