代码如下:
# -*- coding:utf-8 -*-
#http://blog.csdn.net/happen23/article/details/45821697
#百度语音识别API的使用样例(python实现)
#encoding=utf-8
import wave
import urllib, urllib2, pycurl
import base64
import json
## get access token by api key & secret key
def get_token():
apiKey = "xjlSpsvUgGF8a9ltNOtREoTr"
secretKey = "a95ca71b81854b526e7eb04ae8f51d23"
auth_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=" + apiKey + "&client_secret=" + secretKey;
res = urllib2.urlopen(auth_url)
json_data = res.read()
return json.loads(json_data)['access_token']
def dump_res(buf):
print buf
## post audio to server
def use_cloud(token):
fp = wave.open('8k.wav', 'rb')
nf = fp.getnframes()
f_len = nf * 2
audio_data = fp.readframes(nf)
cuid = "xxxxxxxxxx" #my xiaomi phone MAC
srv_url = 'http://vop.baidu.com/server_api' + '?cuid=' + cuid + '&token=' + token
http_header = [
'Content-Type: audio/pcm; rate=8000',
'Content-Length: %d' % f_len
]
c = pycurl.Curl()
c.setopt(pycurl.URL, str(srv_url)) #curl doesn't support unicode
#c.setopt(c.RETURNTRANSFER, 1)
c.setopt(c.HTTPHEADER, http_header) #must be list, not dict
c.setopt(c.POST, 1)
c.setopt(c.CONNECTTIMEOUT, 30)
c.setopt(c.TIMEOUT, 30)
c.setopt(c.WRITEFUNCTION, dump_res)
c.setopt(c.POSTFIELDS, audio_data)
c.setopt(c.POSTFIELDSIZE, f_len)
c.perform() #pycurl.perform() has no return val
if __name__ == "__main__":
token = get_token()
use_cloud(token)
http://yuyin.baidu.com/docs/asr/54
在上面这个链接的页面中,往下拖,可以得到下载链接如下:
http://speech-doc.gz.bcebos.com/rest-api-asr/public_audio/public.zip
然后运行结果:
{"corpus_no":"6485972281376050071","err_msg":"success.","err_no":0,"result":["北京科技馆,"],"sn":"651708407021510133099"}
注意事项:
百度的语音识别和语音合成用的是相同的
appid、API key和Secret Key,所以使用相同的token即可
获取以上三个字段的教程:
http://jingyan.baidu.com/article/f3e34a12df0cddf5eb65359f.html
后记:
下面的代码可以运行任意自己录制的音频文件,注意,运行前必须apt-get install ffmpeg
另外,rate改成了16000,不然会识别不准,不过,也没有经过大量测试,不知道识别准确的情况还会不会出现。
# -*- coding:utf-8 -*-
#http://blog.csdn.net/happen23/article/details/45821697
#百度语音识别API的使用样例(python实现)
#encoding=utf-8
import wave
import urllib, urllib2, pycurl
import base64
import subprocess
import json
## get access token by api key & secret key
def get_token():
apiKey = "xjlSpsvUgGF8a9ltNOtREoTr"
secretKey = "a95ca71b81854b526e7eb04ae8f51d23"
auth_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=" + apiKey + "&client_secret=" + secretKey;
res = urllib2.urlopen(auth_url)
json_data = res.read()
return json.loads(json_data)['access_token']
def dump_res(buf):
print buf
## post audio to server
def use_cloud(token):
subprocess.call(['ffmpeg', '-i', 'tian.mp3', 'tian.wav'])#这句代码的意思是在终端中执行[]中的命令。所以执行的前提是apt-get install ffmpeg
fp = wave.open('tian.wav', 'rb')
nf = fp.getnframes()
f_len = nf * 2
audio_data = fp.readframes(nf)
cuid = "xxxxxxxxxx" #my xiaomi phone MAC
srv_url = 'http://vop.baidu.com/server_api' + '?cuid=' + cuid + '&token=' + token
http_header = [
'Content-Type: audio/pcm; rate=16000',
'Content-Length: %d' % f_len
]
c = pycurl.Curl()
c.setopt(pycurl.URL, str(srv_url)) #curl doesn't support unicode
#c.setopt(c.RETURNTRANSFER, 1)
c.setopt(c.HTTPHEADER, http_header) #must be list, not dict
c.setopt(c.POST, 1)
c.setopt(c.CONNECTTIMEOUT, 30)
c.setopt(c.TIMEOUT, 30)
c.setopt(c.WRITEFUNCTION, dump_res)
c.setopt(c.POSTFIELDS, audio_data)
c.setopt(c.POSTFIELDSIZE, f_len)
c.perform() #pycurl.perform() has no return val
if __name__ == "__main__":
token = get_token()
use_cloud(token)
所谓的离线资源下载,其实仍然是本地向服务器请求,效率上是无法提高的。