add Xunfei Voice

Signed-off-by: njnuko <njnuko@163.com>
This commit is contained in:
njnuko
2024-05-20 15:04:23 +08:00
parent 99aac76618
commit 6fed719e09
5 changed files with 460 additions and 0 deletions

163
voice/xunfei/xunfei_tts.py Normal file
View File

@@ -0,0 +1,163 @@
# -*- coding:utf-8 -*-
#
# Author: njnuko
# Email: njnuko@163.com
#
# 这个文档是基于官方的demo来改的固体官方demo文档请参考官网
#
# 语音听写流式 WebAPI 接口调用示例 接口文档必看https://doc.xfyun.cn/rest_api/语音听写(流式版).html
# webapi 听写服务参考帖子必看http://bbs.xfyun.cn/forum.php?mod=viewthread&tid=38947&extra=
# 语音听写流式WebAPI 服务热词使用方式登陆开放平台https://www.xfyun.cn/后,找到控制台--我的应用---语音听写(流式)---服务管理--个性化热词,
# 设置热词
# 注意:热词只能在识别的时候会增加热词的识别权重,需要注意的是增加相应词条的识别率,但并不是绝对的,具体效果以您测试为准。
# 语音听写流式WebAPI 服务方言试用方法登陆开放平台https://www.xfyun.cn/后,找到控制台--我的应用---语音听写(流式)---服务管理--识别语种列表
# 可添加语种或方言,添加后会显示该方言的参数值
# 错误码链接https://www.xfyun.cn/document/error-code code返回错误码时必看
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
import websocket
import datetime
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import time
import ssl
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import _thread as thread
import os
STATUS_FIRST_FRAME = 0 # 第一帧的标识
STATUS_CONTINUE_FRAME = 1 # 中间帧标识
STATUS_LAST_FRAME = 2 # 最后一帧的标识
#############
#这个参数是用来做输出文件路径的
global outfile
#这个文档是官方文档改的,这个参数是用来做函数调用时用的
global wsParam
##############
class Ws_Param(object):
# 初始化
def __init__(self, APPID, APIKey, APISecret,BusinessArgs,Text):
self.APPID = APPID
self.APIKey = APIKey
self.APISecret = APISecret
self.BusinessArgs = BusinessArgs
self.Text = Text
# 公共参数(common)
self.CommonArgs = {"app_id": self.APPID}
# 业务参数(business),更多个性化参数可在官网查看
#self.BusinessArgs = {"aue": "raw", "auf": "audio/L16;rate=16000", "vcn": "xiaoyan", "tte": "utf8"}
self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-8')), "UTF8")}
#使用小语种须使用以下方式此处的unicode指的是 utf16小端的编码方式即"UTF-16LE"”
#self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-16')), "UTF8")}
# 生成url
def create_url(self):
url = 'wss://tts-api.xfyun.cn/v2/tts'
# 生成RFC1123格式的时间戳
now = datetime.now()
date = format_date_time(mktime(now.timetuple()))
# 拼接字符串
signature_origin = "host: " + "ws-api.xfyun.cn" + "\n"
signature_origin += "date: " + date + "\n"
signature_origin += "GET " + "/v2/tts " + "HTTP/1.1"
# 进行hmac-sha256进行加密
signature_sha = hmac.new(self.APISecret.encode('utf-8'), signature_origin.encode('utf-8'),
digestmod=hashlib.sha256).digest()
signature_sha = base64.b64encode(signature_sha).decode(encoding='utf-8')
authorization_origin = "api_key=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"" % (
self.APIKey, "hmac-sha256", "host date request-line", signature_sha)
authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')
# 将请求的鉴权参数组合为字典
v = {
"authorization": authorization,
"date": date,
"host": "ws-api.xfyun.cn"
}
# 拼接鉴权参数生成url
url = url + '?' + urlencode(v)
# print("date: ",date)
# print("v: ",v)
# 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释比对相同参数时生成的url与自己代码生成的url是否一致
# print('websocket url :', url)
return url
def on_message(ws, message):
#输出文件
global outfile
try:
message =json.loads(message)
code = message["code"]
sid = message["sid"]
audio = message["data"]["audio"]
audio = base64.b64decode(audio)
status = message["data"]["status"]
if status == 2:
print("ws is closed")
ws.close()
if code != 0:
errMsg = message["message"]
print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))
else:
with open(outfile, 'ab') as f:
f.write(audio)
except Exception as e:
print("receive msg,but parse exception:", e)
# 收到websocket连接建立的处理
def on_open(ws):
global outfile
global wsParam
def run(*args):
d = {"common": wsParam.CommonArgs,
"business": wsParam.BusinessArgs,
"data": wsParam.Data,
}
d = json.dumps(d)
print("------>开始发送文本数据")
ws.send(d)
if os.path.exists(outfile):
os.remove(outfile)
thread.start_new_thread(run, ())
# 收到websocket错误的处理
def on_error(ws, error):
print("### error:", error)
# 收到websocket关闭的处理
def on_close(ws):
print("### closed ###")
def xunfei_tts(APPID, APIKey, APISecret,BusinessArgsTTS, Text, OutFile):
global outfile
global wsParam
outfile = OutFile
wsParam1 = Ws_Param(APPID,APIKey,APISecret,BusinessArgsTTS,Text)
wsParam = wsParam1
websocket.enableTrace(False)
wsUrl = wsParam.create_url()
ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close)
ws.on_open = on_open
ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})
return outfile