Browse Source

Merge branch 'master' into wechatcom_app

master
Saboteur7 GitHub 3 months ago
parent
commit
3e4969efe6
No known key found for this signature in database GPG Key ID: B5690EEEBB952194
8 changed files with 97 additions and 10 deletions
  1. +1
    -1
      bot/chatgpt/chat_gpt_session.py
  2. +2
    -1
      bot/linkai/link_ai_bot.py
  3. +2
    -1
      common/const.py
  4. +1
    -1
      config.py
  5. +1
    -1
      plugins/source.json
  6. +64
    -0
      voice/ali/ali_api.py
  7. +24
    -4
      voice/ali/ali_voice.py
  8. +2
    -1
      voice/ali/config.json.template

+ 1
- 1
bot/chatgpt/chat_gpt_session.py View File

@@ -67,7 +67,7 @@ def num_tokens_from_messages(messages, model):
elif model in ["gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0613", "gpt-3.5-turbo-0613",
"gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-35-turbo-16k", "gpt-4-turbo-preview",
"gpt-4-1106-preview", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW, const.GPT4_TURBO_01_25,
const.GPT_4o, const.LINKAI_4o, const.LINKAI_4_TURBO]:
const.GPT_4o, const.GPT_4o_MINI, const.LINKAI_4o, const.LINKAI_4_TURBO]:
return num_tokens_from_messages(messages, model="gpt-4")
elif model.startswith("claude-3"):
return num_tokens_from_messages(messages, model="gpt-3.5-turbo")


+ 2
- 1
bot/linkai/link_ai_bot.py View File

@@ -399,6 +399,7 @@ class LinkAIBot(Bot):
return
max_send_num = conf().get("max_media_send_count")
send_interval = conf().get("media_send_interval")
file_type = (".pdf", ".doc", ".docx", ".csv", ".xls", ".xlsx", ".txt", ".rtf", ".ppt", ".pptx")
try:
i = 0
for url in image_urls:
@@ -407,7 +408,7 @@ class LinkAIBot(Bot):
i += 1
if url.endswith(".mp4"):
reply_type = ReplyType.VIDEO_URL
elif url.endswith(".pdf") or url.endswith(".doc") or url.endswith(".docx") or url.endswith(".csv"):
elif url.endswith(file_type):
reply_type = ReplyType.FILE
url = _download_file(url)
if not url:


+ 2
- 1
common/const.py View File

@@ -32,6 +32,7 @@ GPT4_TURBO_11_06 = "gpt-4-1106-preview"
GPT4_VISION_PREVIEW = "gpt-4-vision-preview"

GPT4 = "gpt-4"
GPT_4o_MINI = "gpt-4o-mini"
GPT4_32k = "gpt-4-32k"
GPT4_06_13 = "gpt-4-0613"
GPT4_32k_06_13 = "gpt-4-32k-0613"
@@ -57,7 +58,7 @@ GEMINI_15_PRO = "gemini-1.5-pro"

MODEL_LIST = [
GPT35, GPT35_0125, GPT35_1106, "gpt-3.5-turbo-16k",
GPT_4o, GPT4_TURBO, GPT4_TURBO_PREVIEW, GPT4_TURBO_01_25, GPT4_TURBO_11_06, GPT4, GPT4_32k, GPT4_06_13, GPT4_32k_06_13,
GPT_4o, GPT_4o_MINI, GPT4_TURBO, GPT4_TURBO_PREVIEW, GPT4_TURBO_01_25, GPT4_TURBO_11_06, GPT4, GPT4_32k, GPT4_06_13, GPT4_32k_06_13,
WEN_XIN, WEN_XIN_4,
XUNFEI, ZHIPU_AI, MOONSHOT, MiniMax,
GEMINI, GEMINI_PRO, GEMINI_15_flash, GEMINI_15_PRO,


+ 1
- 1
config.py View File

@@ -17,7 +17,7 @@ available_setting = {
"open_ai_api_base": "https://api.openai.com/v1",
"proxy": "", # openai使用的代理
# 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", # 可选择: gpt-4o, gpt-4-turbo, claude-3-sonnet, wenxin, moonshot, qwen-turbo, xunfei, glm-4, minimax, gemini等模型,全部可选模型详见common/const.py文件
"model": "gpt-3.5-turbo", # 可选择: gpt-4o, pt-4o-mini, gpt-4-turbo, claude-3-sonnet, wenxin, moonshot, qwen-turbo, xunfei, glm-4, minimax, gemini等模型,全部可选模型详见common/const.py文件
"bot_type": "", # 可选配置,使用兼容openai格式的三方服务时候,需填"chatGPT"。bot具体名称详见common/const.py文件列出的bot_type,如不填根据model名称判断,
"use_azure_chatgpt": False, # 是否使用azure的chatgpt
"azure_deployment_id": "", # azure 模型部署名称


+ 1
- 1
plugins/source.json View File

@@ -22,7 +22,7 @@
},
"pictureChange": {
"url": "https://github.com/Yanyutin753/pictureChange.git",
"desc": "利用stable-diffusion和百度Ai进行图生图或者画图的插件"
"desc": "1. 支持百度AI和Stable Diffusion WebUI进行图像处理,提供多种模型选择,支持图生图、文生图自定义模板。2. 支持Suno音乐AI可将图像和文字转为音乐。3. 支持自定义模型进行文件、图片总结功能。4. 支持管理员控制群聊内容与参数和功能改变。"
},
"Blackroom": {
"url": "https://github.com/dividduang/blackroom.git",


+ 64
- 0
voice/ali/ali_api.py View File

@@ -8,6 +8,7 @@ Description:

"""

import http.client
import json
import time
import requests
@@ -61,6 +62,69 @@ def text_to_speech_aliyun(url, text, appkey, token):

return output_file

def speech_to_text_aliyun(url, audioContent, appkey, token):
"""
使用阿里云的语音识别服务识别音频文件中的语音。

参数:
- url (str): 阿里云语音识别服务的端点URL。
- audioContent (byte): pcm音频数据。
- appkey (str): 您的阿里云appkey。
- token (str): 阿里云API的认证令牌。

返回值:
- str: 成功时输出识别到的文本,否则为None。
"""
format = 'pcm'
sample_rate = 16000
enablePunctuationPrediction = True
enableInverseTextNormalization = True
enableVoiceDetection = False

# 设置RESTful请求参数
request = url + '?appkey=' + appkey
request = request + '&format=' + format
request = request + '&sample_rate=' + str(sample_rate)

if enablePunctuationPrediction :
request = request + '&enable_punctuation_prediction=' + 'true'

if enableInverseTextNormalization :
request = request + '&enable_inverse_text_normalization=' + 'true'

if enableVoiceDetection :
request = request + '&enable_voice_detection=' + 'true'
host = 'nls-gateway-cn-shanghai.aliyuncs.com'

# 设置HTTPS请求头部
httpHeaders = {
'X-NLS-Token': token,
'Content-type': 'application/octet-stream',
'Content-Length': len(audioContent)
}

conn = http.client.HTTPSConnection(host)
conn.request(method='POST', url=request, body=audioContent, headers=httpHeaders)

response = conn.getresponse()
body = response.read()
try:
body = json.loads(body)
status = body['status']
if status == 20000000 :
result = body['result']
if result :
logger.info(f"阿里云语音识别到了:{result}")
conn.close()
return result
else :
logger.error(f"语音识别失败,状态码: {status}")
except ValueError:
logger.error(f"语音识别失败,收到非JSON格式的数据: {body}")
conn.close()
return None


class AliyunTokenGenerator:
"""


+ 24
- 4
voice/ali/ali_voice.py View File

@@ -15,9 +15,9 @@ import time

from bridge.reply import Reply, ReplyType
from common.log import logger
from voice.audio_convert import get_pcm_from_wav
from voice.voice import Voice
from voice.ali.ali_api import AliyunTokenGenerator
from voice.ali.ali_api import text_to_speech_aliyun
from voice.ali.ali_api import AliyunTokenGenerator, speech_to_text_aliyun, text_to_speech_aliyun
from config import conf


@@ -34,7 +34,8 @@ class AliVoice(Voice):
self.token = None
self.token_expire_time = 0
# 默认复用阿里云千问的 access_key 和 access_secret
self.api_url = config.get("api_url")
self.api_url_voice_to_text = config.get("api_url_voice_to_text")
self.api_url_text_to_voice = config.get("api_url_text_to_voice")
self.app_key = config.get("app_key")
self.access_key_id = conf().get("qwen_access_key_id") or config.get("access_key_id")
self.access_key_secret = conf().get("qwen_access_key_secret") or config.get("access_key_secret")
@@ -53,7 +54,7 @@ class AliVoice(Voice):
r'äöüÄÖÜáéíóúÁÉÍÓÚàèìòùÀÈÌÒÙâêîôûÂÊÎÔÛçÇñÑ,。!?,.]', '', text)
# 提取有效的token
token_id = self.get_valid_token()
fileName = text_to_speech_aliyun(self.api_url, text, self.app_key, token_id)
fileName = text_to_speech_aliyun(self.api_url_text_to_voice, text, self.app_key, token_id)
if fileName:
logger.info("[Ali] textToVoice text={} voice file name={}".format(text, fileName))
reply = Reply(ReplyType.VOICE, fileName)
@@ -61,6 +62,25 @@ class AliVoice(Voice):
reply = Reply(ReplyType.ERROR, "抱歉,语音合成失败")
return reply

def voiceToText(self, voice_file):
"""
将语音文件转换为文本。

:param voice_file: 要转换的语音文件。
:return: 返回一个Reply对象,其中包含转换得到的文本或错误信息。
"""
# 提取有效的token
token_id = self.get_valid_token()
logger.debug("[Ali] voice file name={}".format(voice_file))
pcm = get_pcm_from_wav(voice_file)
text = speech_to_text_aliyun(self.api_url_voice_to_text, pcm, self.app_key, token_id)
if text:
logger.info("[Ali] VoicetoText = {}".format(text))
reply = Reply(ReplyType.TEXT, text)
else:
reply = Reply(ReplyType.ERROR, "抱歉,语音识别失败")
return reply

def get_valid_token(self):
"""
获取有效的阿里云token。


+ 2
- 1
voice/ali/config.json.template View File

@@ -1,5 +1,6 @@
{
"api_url": "https://nls-gateway-cn-shanghai.aliyuncs.com/stream/v1/tts",
"api_url_text_to_voice": "https://nls-gateway-cn-shanghai.aliyuncs.com/stream/v1/tts",
"api_url_voice_to_text": "https://nls-gateway.cn-shanghai.aliyuncs.com/stream/v1/asr",
"app_key": "",
"access_key_id": "",
"access_key_secret": ""

Loading…
Cancel
Save