python百度语音实时识别成文字_python 上传百度语音识别+文字返回结果

1文字生成语音

#!/usr/bin/python3

import urllib.request

import requests#导入requests库

import urllib

import json

import base64

class BaiduRest:

def __init__(self, cu_id, api_key, api_secert):

# token认证的url

self.token_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=%s&client_secret=%s"

# 语音合成的resturl

self.getvoice_url = "http://tsn.baidu.com/text2audio?tex=%s&lan=zh&cuid=%s&ctp=1&tok=%s"

# 语音识别的resturl

self.upvoice_url = 'http://vop.baidu.com/server_api'

self.cu_id = cu_id

self.getToken(api_key, api_secert)

return

def getToken(self, api_key, api_secert):

# 1.获取token

token_url = self.token_url % (api_key,api_secert)

r_str = requests.get(token_url).text

token_data = json.loads(r_str)

self.token_str = token_data['access_token']

pass

def getVoice(self, text, filename):

# 2. 向Rest接口提交数据

get_url = self.getvoice_url % (urllib.parse.quote(text), self.cu_id, self.token_str)

voice_data = urllib.request.urlopen(get_url).read()

# 3.处理返回数据

voice_fp = open(filename,'wb+')

voice_fp.write(voice_data)

voice_fp.close()

pass

def getText(self, filename):

# 2. 向Rest接口提交数据

data = {}

# 语音的一些参数

data['format'] = 'wav'

data['rate'] = 8000

data['channel'] = 1

data['cuid'] = self.cu_id

data['token'] = self.token_str

wav_fp = open(filename,'rb')

voice_data = wav_fp.read()

data['len'] = len(voice_data)

data['speech'] = base64.b64encode(voice_data).decode('utf-8')

post_data = json.dumps(data)

# data=bytes(post_data,encoding="utf-8")

url=self.upvoice_url+post_data

r_data = requests.get(url).text

# 3.处理返回数据

return json.loads(r_data)['result']

if __name__ == "__main__":

# 我的api_key,供大家测试用，在实际工程中请换成自己申请的应用的key和secert

api_key = "SrhYKqzl3SE1URnAEuZ0FKdT"

api_secert = "hGqeCkaMPb0ELMqtRGc2VjWdmjo7T89d"

# 初始化

bdr = BaiduRest("test_python", api_key, api_secert)

# 将字符串语音合成并保存为out.mp3

bdr.getVoice("你好北京邮电大学!我是瑶瑶", "out.mp3")

# 识别test.wav语音内容并显示

print(bdr.getText("1.wav"))