百度语音识别

# coding=utf-8

import sys
import json
import base64
import time

#判断python版本 初始化库
IS_PY3 = sys.version_info.major == 3

if IS_PY3:
    from urllib.request import urlopen
    from urllib.request import Request
    from urllib.error import URLError
    from urllib.parse import urlencode
    timer = time.perf_counter
else:
    from urllib2 import urlopen
    from urllib2 import Request
    from urllib2 import URLError
    from urllib import urlencode
    if sys.platform == "win32":
        timer = time.clock
    else:
        # On most other platforms the best timer is time.time()
        timer = time.time
#百度设备API信息
API_KEY = 'kVcnfD9iW2XVZSMaLMrtLYIz'
SECRET_KEY = 'O9o1O213UgG5LFn0bDGNtoRN3VWl2du6'

# 需要识别的文件
AUDIO_FILE = './pcm/16k.pcm'  # 只支持 pcm/wav/amr
# 文件格式
FORMAT = AUDIO_FILE[-3:]  # 文件后缀只支持 pcm/wav/amr
#用户唯一标识，用来区分用户，计算UV值。建议填写能区分用户的机器 MAC 地址或 IMEI 码，长度为60字符以内。
CUID = '123456PYTHON'
# 采样率
RATE = 16000  # 固定值

# 免费版

DEV_PID = 1536  # 1537 表示识别普通话，使用输入法模型。1536表示识别普通话，使用搜索模型。根据文档填写PID，选择语言及识别模型
ASR_URL = 'http://vop.baidu.com/server_api'
SCOPE = 'audio_voice_assistant_get'  # 有此scope表示有asr能力，没有请在网页里勾选，非常旧的应用可能没有

# 收费极速版 打开注释的话请填写自己申请的appkey appSecret ，并在网页中开通极速版

# DEV_PID = 80001
# ASR_URL = 'https://vop.baidu.com/pro_api'
# SCOPE = 'brain_enhanced_asr'  # 有此scope表示有收费极速版能力，没有请在网页里开通极速版

# 忽略scope检查，非常旧的应用可能没有
# SCOPE = False

class DemoError(Exception):
    pass


"""  TOKEN start """
#请求URL
TOKEN_URL = 'http://openapi.baidu.com/oauth/2.0/token'


def fetch_token():
    params = {'grant_type': 'client_credentials',
              'client_id': API_KEY,
              'client_secret': SECRET_KEY}
    post_data = urlencode(params)
    if (IS_PY3):
        post_data = post_data.encode( 'utf-8')
    req = Request(TOKEN_URL, post_data)
    try:
        f = urlopen(req)
        result_str = f.read()
    except URLError as err:
        print('token http response http code : ' + str(err.code))
        result_str = err.read()
    if (IS_PY3):
        result_str =  result_str.decode()

    print(result_str)
    result = json.loads(result_str)
    print(result)
    if ('access_token' in result.keys() and 'scope' in result.keys()):
        print(SCOPE)
        if SCOPE and (not SCOPE in result['scope'].split(' ')):  # SCOPE = False 忽略检查
            raise DemoError('scope is not correct')
        print('SUCCESS WITH TOKEN: %s  EXPIRES IN SECONDS: %s' % (result['access_token'], result['expires_in']))
        return result['access_token']
    else:
        raise DemoError('MAYBE API_KEY or SECRET_KEY not correct: access_token or scope not found in token response')

"""  TOKEN end """

if __name__ == '__main__':
##f获取令牌开始 具体见百度语音合成tty   https://blog.csdn.net/qq_25205045/article/details/90454082
    token = fetch_token()

    speech_data = []
    #打开识别的文件到定义的语音文件数据中
    with open(AUDIO_FILE, 'rb') as speech_file:
        speech_data = speech_file.read()
	#读取打开文件数据长度并对其进行判断处理
    length = len(speech_data)
    if length == 0:
        raise DemoError('file %s length read 0 bytes' % AUDIO_FILE)
     #对数据进行转码
    speech = base64.b64encode(speech_data)
    if (IS_PY3):
        speech = str(speech, 'utf-8')
    params = {'dev_pid': DEV_PID,
              'format': FORMAT,
              'rate': RATE,
              'token': token,
              'cuid': CUID,
              'channel': 1,
              'speech': speech,
              'len': length
              }
    post_data = json.dumps(params, sort_keys=False)
    # print post_data
    req = Request(ASR_URL, post_data.encode('utf-8'))
    req.add_header('Content-Type', 'application/json')
    try:
        begin = timer()
        f = urlopen(req)
        result_str = f.read()
        print ("Request time cost %f" % (timer() - begin))
    except URLError as err:
        print('asr http response http code : ' + str(err.code))
        result_str = err.read()

    if (IS_PY3):
        result_str = str(result_str, 'utf-8')
    print(result_str)
    with open("result.txt","w") as of:
        of.write(result_str)