mirror of
https://github.com/zhayujie/chatgpt-on-wechat.git
synced 2026-07-21 06:07:13 +08:00
增加百度语音识别
This commit is contained in:
99
config.py
99
config.py
@@ -5,71 +5,76 @@ import os
|
|||||||
from common.log import logger
|
from common.log import logger
|
||||||
|
|
||||||
# 将所有可用的配置项写在字典里, 请使用小写字母
|
# 将所有可用的配置项写在字典里, 请使用小写字母
|
||||||
available_setting ={
|
available_setting = {
|
||||||
#openai api配置
|
# openai api配置
|
||||||
"open_ai_api_key": "", # openai api key
|
"open_ai_api_key": "", # openai api key
|
||||||
"open_ai_api_base": "https://api.openai.com/v1", # openai apibase,当use_azure_chatgpt为true时,需要设置对应的api base
|
# openai apibase,当use_azure_chatgpt为true时,需要设置对应的api base
|
||||||
"proxy": "", # openai使用的代理
|
"open_ai_api_base": "https://api.openai.com/v1",
|
||||||
"model": "gpt-3.5-turbo", # chatgpt模型, 当use_azure_chatgpt为true时,其名称为Azure上model deployment名称
|
"proxy": "", # openai使用的代理
|
||||||
"use_azure_chatgpt": False, # 是否使用azure的chatgpt
|
# chatgpt模型, 当use_azure_chatgpt为true时,其名称为Azure上model deployment名称
|
||||||
|
"model": "gpt-3.5-turbo",
|
||||||
|
"use_azure_chatgpt": False, # 是否使用azure的chatgpt
|
||||||
|
|
||||||
#Bot触发配置
|
# Bot触发配置
|
||||||
"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_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
|
"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_chat_prefix": ["@bot"], # 群聊时包含该前缀则会触发机器人回复
|
||||||
"group_chat_reply_prefix": "", # 群聊时自动回复的前缀
|
"group_chat_reply_prefix": "", # 群聊时自动回复的前缀
|
||||||
"group_chat_keyword": [], # 群聊时包含该关键词则会触发机器人回复
|
"group_chat_keyword": [], # 群聊时包含该关键词则会触发机器人回复
|
||||||
"group_at_off": False, # 是否关闭群聊时@bot的触发
|
"group_at_off": False, # 是否关闭群聊时@bot的触发
|
||||||
"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
|
"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
|
||||||
"group_name_keyword_white_list": [], # 开启自动回复的群名称关键词列表
|
"group_name_keyword_white_list": [], # 开启自动回复的群名称关键词列表
|
||||||
"group_chat_in_one_session": ["ChatGPT测试群"], # 支持会话上下文共享的群名称
|
"group_chat_in_one_session": ["ChatGPT测试群"], # 支持会话上下文共享的群名称
|
||||||
"image_create_prefix": ["画", "看", "找"], # 开启图片回复的前缀
|
"image_create_prefix": ["画", "看", "找"], # 开启图片回复的前缀
|
||||||
|
|
||||||
#chatgpt会话参数
|
# chatgpt会话参数
|
||||||
"expires_in_seconds": 3600, # 无操作会话的过期时间
|
"expires_in_seconds": 3600, # 无操作会话的过期时间
|
||||||
"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
|
"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
|
||||||
"conversation_max_tokens": 1000, # 支持上下文记忆的最多字符数
|
"conversation_max_tokens": 1000, # 支持上下文记忆的最多字符数
|
||||||
|
|
||||||
#chatgpt限流配置
|
# chatgpt限流配置
|
||||||
"rate_limit_chatgpt": 20, # chatgpt的调用频率限制
|
"rate_limit_chatgpt": 20, # chatgpt的调用频率限制
|
||||||
"rate_limit_dalle": 50, # openai dalle的调用频率限制
|
"rate_limit_dalle": 50, # openai dalle的调用频率限制
|
||||||
|
|
||||||
|
|
||||||
#chatgpt api参数 参考https://platform.openai.com/docs/api-reference/chat/create
|
# chatgpt api参数 参考https://platform.openai.com/docs/api-reference/chat/create
|
||||||
"temperature": 0.9,
|
"temperature": 0.9,
|
||||||
"top_p": 1,
|
"top_p": 1,
|
||||||
"frequency_penalty": 0,
|
"frequency_penalty": 0,
|
||||||
"presence_penalty": 0,
|
"presence_penalty": 0,
|
||||||
|
|
||||||
#语音设置
|
# 语音设置
|
||||||
"speech_recognition": False, # 是否开启语音识别
|
"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
|
"group_speech_recognition": False, # 是否开启群组语音识别
|
||||||
"voice_reply_voice": False, # 是否使用语音回复语音,需要设置对应语音合成引擎的api key
|
"voice_reply_voice": False, # 是否使用语音回复语音,需要设置对应语音合成引擎的api key
|
||||||
"voice_to_text": "openai", # 语音识别引擎,支持openai和google
|
"voice_to_text": "openai", # 语音识别引擎,支持openai和google
|
||||||
"text_to_voice": "baidu", # 语音合成引擎,支持baidu和google
|
"text_to_voice": "baidu", # 语音合成引擎,支持baidu和google
|
||||||
|
|
||||||
# baidu api的配置, 使用百度语音识别和语音合成时需要
|
# baidu api的配置, 使用百度语音识别和语音合成时需要
|
||||||
'baidu_app_id': "",
|
"baidu_app_id": "",
|
||||||
'baidu_api_key': "",
|
"baidu_api_key": "",
|
||||||
'baidu_secret_key': "",
|
"baidu_secret_key": "",
|
||||||
|
# 1536普通话(支持简单的英文识别) 1737英语 1637粤语 1837四川话 1936普通话远场
|
||||||
|
"baidu_dev_pid": "1536",
|
||||||
|
|
||||||
#服务时间限制,目前支持itchat
|
# 服务时间限制,目前支持itchat
|
||||||
"chat_time_module": False, # 是否开启服务时间限制
|
"chat_time_module": False, # 是否开启服务时间限制
|
||||||
"chat_start_time": "00:00", # 服务开始时间
|
"chat_start_time": "00:00", # 服务开始时间
|
||||||
"chat_stop_time": "24:00", # 服务结束时间
|
"chat_stop_time": "24:00", # 服务结束时间
|
||||||
|
|
||||||
# itchat的配置
|
# itchat的配置
|
||||||
"hot_reload": False, # 是否开启热重载
|
"hot_reload": False, # 是否开启热重载
|
||||||
|
|
||||||
# wechaty的配置
|
# wechaty的配置
|
||||||
"wechaty_puppet_service_token": "", # wechaty的token
|
"wechaty_puppet_service_token": "", # wechaty的token
|
||||||
|
|
||||||
# chatgpt指令自定义触发词
|
# chatgpt指令自定义触发词
|
||||||
"clear_memory_commands": ['#清除记忆'], # 重置会话指令
|
"clear_memory_commands": ['#清除记忆'], # 重置会话指令
|
||||||
|
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
class Config(dict):
|
class Config(dict):
|
||||||
def __getitem__(self, key):
|
def __getitem__(self, key):
|
||||||
if key not in available_setting:
|
if key not in available_setting:
|
||||||
@@ -82,15 +87,17 @@ class Config(dict):
|
|||||||
return super().__setitem__(key, value)
|
return super().__setitem__(key, value)
|
||||||
|
|
||||||
def get(self, key, default=None):
|
def get(self, key, default=None):
|
||||||
try :
|
try:
|
||||||
return self[key]
|
return self[key]
|
||||||
except KeyError as e:
|
except KeyError as e:
|
||||||
return default
|
return default
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
raise e
|
raise e
|
||||||
|
|
||||||
|
|
||||||
config = Config()
|
config = Config()
|
||||||
|
|
||||||
|
|
||||||
def load_config():
|
def load_config():
|
||||||
global config
|
global config
|
||||||
config_path = "./config.json"
|
config_path = "./config.json"
|
||||||
@@ -109,7 +116,8 @@ def load_config():
|
|||||||
for name, value in os.environ.items():
|
for name, value in os.environ.items():
|
||||||
name = name.lower()
|
name = name.lower()
|
||||||
if name in available_setting:
|
if name in available_setting:
|
||||||
logger.info("[INIT] override config by environ args: {}={}".format(name, value))
|
logger.info(
|
||||||
|
"[INIT] override config by environ args: {}={}".format(name, value))
|
||||||
try:
|
try:
|
||||||
config[name] = eval(value)
|
config[name] = eval(value)
|
||||||
except:
|
except:
|
||||||
@@ -118,9 +126,8 @@ def load_config():
|
|||||||
logger.info("[INIT] load config: {}".format(config))
|
logger.info("[INIT] load config: {}".format(config))
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
def get_root():
|
def get_root():
|
||||||
return os.path.dirname(os.path.abspath( __file__ ))
|
return os.path.dirname(os.path.abspath(__file__))
|
||||||
|
|
||||||
|
|
||||||
def read_file(path):
|
def read_file(path):
|
||||||
|
|||||||
@@ -8,19 +8,53 @@ from bridge.reply import Reply, ReplyType
|
|||||||
from common.log import logger
|
from common.log import logger
|
||||||
from common.tmp_dir import TmpDir
|
from common.tmp_dir import TmpDir
|
||||||
from voice.voice import Voice
|
from voice.voice import Voice
|
||||||
|
from voice.audio_convert import get_pcm_from_wav
|
||||||
from config import conf
|
from config import conf
|
||||||
|
"""
|
||||||
|
百度的语音识别API.
|
||||||
|
dev_pid:
|
||||||
|
- 1936: 普通话远场
|
||||||
|
- 1536:普通话(支持简单的英文识别)
|
||||||
|
- 1537:普通话(纯中文识别)
|
||||||
|
- 1737:英语
|
||||||
|
- 1637:粤语
|
||||||
|
- 1837:四川话
|
||||||
|
要使用本模块, 首先到 yuyin.baidu.com 注册一个开发者账号,
|
||||||
|
之后创建一个新应用, 然后在应用管理的"查看key"中获得 API Key 和 Secret Key
|
||||||
|
填入 config.json 中.
|
||||||
|
baidu_app_id: ''
|
||||||
|
baidu_api_key: ''
|
||||||
|
baidu_secret_key: ''
|
||||||
|
baidu_dev_pid: '1536'
|
||||||
|
"""
|
||||||
|
|
||||||
|
|
||||||
class BaiduVoice(Voice):
|
class BaiduVoice(Voice):
|
||||||
APP_ID = conf().get('baidu_app_id')
|
APP_ID = conf().get('baidu_app_id')
|
||||||
API_KEY = conf().get('baidu_api_key')
|
API_KEY = conf().get('baidu_api_key')
|
||||||
SECRET_KEY = conf().get('baidu_secret_key')
|
SECRET_KEY = conf().get('baidu_secret_key')
|
||||||
|
DEV_ID = conf().get('baidu_dev_pid')
|
||||||
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
|
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
|
||||||
|
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
pass
|
pass
|
||||||
|
|
||||||
def voiceToText(self, voice_file):
|
def voiceToText(self, voice_file):
|
||||||
pass
|
# 识别本地文件
|
||||||
|
logger.debug('[Baidu] voice file name={}'.format(voice_file))
|
||||||
|
pcm = get_pcm_from_wav(voice_file)
|
||||||
|
res = self.client.asr(pcm, "pcm", 16000, {"dev_pid": self.DEV_ID})
|
||||||
|
if res["err_no"] == 0:
|
||||||
|
logger.info("百度语音识别到了:{}".format(res["result"]))
|
||||||
|
text = "".join(res["result"])
|
||||||
|
reply = Reply(ReplyType.TEXT, text)
|
||||||
|
else:
|
||||||
|
logger.info("百度语音识别出错了: {}".format(res["err_msg"]))
|
||||||
|
if res["err_msg"] == "request pv too much":
|
||||||
|
logger.info(" 出现这个原因很可能是你的百度语音服务调用量超出限制,或未开通付费")
|
||||||
|
reply = Reply(ReplyType.ERROR,
|
||||||
|
"百度语音识别出错了;{0}".format(res["err_msg"]))
|
||||||
|
return reply
|
||||||
|
|
||||||
def textToVoice(self, text):
|
def textToVoice(self, text):
|
||||||
result = self.client.synthesis(text, 'zh', 1, {
|
result = self.client.synthesis(text, 'zh', 1, {
|
||||||
@@ -30,7 +64,8 @@ class BaiduVoice(Voice):
|
|||||||
fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
|
fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
|
||||||
with open(fileName, 'wb') as f:
|
with open(fileName, 'wb') as f:
|
||||||
f.write(result)
|
f.write(result)
|
||||||
logger.info('[Baidu] textToVoice text={} voice file name={}'.format(text, fileName))
|
logger.info(
|
||||||
|
'[Baidu] textToVoice text={} voice file name={}'.format(text, fileName))
|
||||||
reply = Reply(ReplyType.VOICE, fileName)
|
reply = Reply(ReplyType.VOICE, fileName)
|
||||||
else:
|
else:
|
||||||
logger.error('[Baidu] textToVoice error={}'.format(result))
|
logger.error('[Baidu] textToVoice error={}'.format(result))
|
||||||
|
|||||||
Reference in New Issue
Block a user