科大讯飞语音的应用

最近想用科大讯飞做一个语音识别的软件,可惜老是出错。(采用python验证)
不知道有什么好的指南?

科大讯飞文档

快速指引还是很清晰

第一步:注册成为开发者

进入讯飞开放平台快捷登录页 ,通过微信扫码、手机快捷登录,即可快速成为讯飞开放平台注册开发者。或进入讯飞开放平台注册页注册完整的开放平台账号,成为讯飞开放平台注册开发者

注册后可以得到开发者的信息

下载demo : tts_ws_python3_demo.py

代码

# -*- coding:utf-8 -*-
#
#   author: iflytek
#
#  本demo测试时运行的环境为:Windows + Python3.7
#  本demo测试成功运行时所安装的第三方库及其版本如下:
#   cffi==1.12.3
#   gevent==1.4.0
#   greenlet==0.4.15
#   pycparser==2.19
#   six==1.12.0
#   websocket==0.2.1
#   websocket-client==0.56.0
#   合成小语种需要传输小语种文本、使用小语种发音人vcn、tte=unicode以及修改文本编码方式
#  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


class Ws_Param(object):
    # 初始化
    def __init__(self, APPID, APIKey, APISecret, Text):
        self.APPID = APPID
        self.APIKey = APIKey
        self.APISecret = APISecret
        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):
    try:
        message =json.loads(message)
        code = message["code"]
        sid = message["sid"]
        audio = message["data"]["audio"]
        audio = base64.b64decode(audio)
        status = message["data"]["status"]
        print(message)
        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('./demo.pcm', 'ab') as f:
                f.write(audio)

    except Exception as e:
        print("receive msg,but parse exception:", e)



# 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 ###")


# 收到websocket连接建立的处理
def on_open(ws):
    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('./demo.pcm'):
            os.remove('./demo.pcm')

    thread.start_new_thread(run, ())


if __name__ == "__main__":
    # 测试时候在此处正确填写相关信息即可运行
    wsParam = Ws_Param(APPID='****', APIKey='******',
                       APISecret='*****',
                       Text="这是一个语音合成示例")
    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})

提示错误
在这里插入图片描述

如果用OCR测试(ocr.py)

# -*- coding: utf-8 -*-
from urllib import parse
import base64
import hashlib
import time
import requests
import json
# """
#   手写文字识别WebAPI接口调用示例接口文档(必看):https://doc.xfyun.cn/rest_api/%E6%89%8B%E5%86%99%E6%96%87%E5%AD%97%E8%AF%86%E5%88%AB.html
#   图片属性:jpg/png/bmp,最短边至少15px,最长边最大4096px,编码后大小不超过4M,识别文字语种:中英文
#   webapi OCR服务参考帖子(必看):http://bbs.xfyun.cn/forum.php?mod=viewthread&tid=39111&highlight=OCR
#   (Very Important)创建完webapi应用添加服务之后一定要设置ip白名单,找到控制台--我的应用--设置ip白名单,如何设置参考:http://bbs.xfyun.cn/forum.php?mod=viewthread&tid=41891
#   错误码链接:https://www.xfyun.cn/document/error-code (code返回错误码时必看)
#   @author iflytek
# """
# OCR手写文字识别接口地址
URL = "http://webapi.xfyun.cn/v1/service/v1/ocr/handwriting"
# 应用APPID(必须为webapi类型应用,并开通手写文字识别服务,参考帖子如何创建一个webapi应用:http://bbs.xfyun.cn/forum.php?mod=viewthread&tid=36481)
APPID = "****"
# 接口密钥(webapi类型应用开通手写文字识别后,控制台--我的应用---手写文字识别---相应服务的apikey)
API_KEY = "*****"
def getHeader():
    curTime = str(int(time.time()))
    param = "{\"language\":\""+language+"\",\"location\":\""+location+"\"}"
    paramBase64 = base64.b64encode(param.encode('utf-8'))

    m2 = hashlib.md5()
    str1 = API_KEY + curTime + str(paramBase64, 'utf-8')
    m2.update(str1.encode('utf-8'))
    checkSum = m2.hexdigest()
	# 组装http请求头
    header = {
        'X-CurTime': curTime,
        'X-Param': paramBase64,
        'X-Appid': APPID,
        'X-CheckSum': checkSum,
        'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
    }
    return header
def getBody(filepath):
    with open(filepath, 'rb') as f:
        imgfile = f.read()
    data = {'image': str(base64.b64encode(imgfile), 'utf-8')}
    return data
# 语种设置
language = "en"
# 是否返回文本位置信息
location = "true"
# 图片上传接口地址
picFilePath = "ocr.jpg"
# headers=getHeader(language, location)
r = requests.post(URL, headers=getHeader(), data=getBody(picFilePath))
print(r.content)

识别结果
科大讯飞语音的应用_第1张图片

你可能感兴趣的:(算法,Python,人工智能)