最近在学习python,做一些python练习题
github上几年前的练习题
有一题是这样的:
使用 Python 实现:对着电脑吼一声,自动打开浏览器中的默认网站。
例如,对着笔记本电脑吼一声“百度”,浏览器自动打开百度首页。
然后开始search相应的功能需要的模块(windows10),理一下思路:
所需模块:
为什么要用百度语音识别api呢?因为免费试用。。
不多说,登录百度云,创建应用
查看文档REST API文档
文档写的蛮详细的,简单概括就是
选择2.
语音格式
格式支持:pcm(不压缩)、wav(不压缩,pcm编码)、amr(压缩格式)。推荐pcm 采样率 :16000 固定值。 编码:16bit 位深的单声道。
百度服务端会将非pcm格式,转为pcm格式,因此使用wav、amr会有额外的转换耗时。
保存为pcm格式可以识别,只是windows自带播放器识别不了pcm格式的,所以改用wav格式,毕竟用的模块是wave
首先是本地录音
import wave
from pyaudio import PyAudio, paInt16
framerate = 16000 # 采样率
num_samples = 2000 # 采样点
channels = 1 # 声道
sampwidth = 2 # 采样宽度2bytes
FILEPATH = 'speech.wav'
def save_wave_file(filepath, data):
wf = wave.open(filepath, 'wb')
wf.setnchannels(channels)
wf.setsampwidth(sampwidth)
wf.setframerate(framerate)
wf.writeframes(b''.join(data))
wf.close()
#录音
def my_record():
pa = PyAudio()
#打开一个新的音频stream
stream = pa.open(format=paInt16, channels=channels,
rate=framerate, input=True, frames_per_buffer=num_samples)
my_buf = [] #存放录音数据
t = time.time()
print('正在录音...')
while time.time() < t + 4: # 设置录音时间(秒)
#循环read,每次read 2000frames
string_audio_data = stream.read(num_samples)
my_buf.append(string_audio_data)
print('录音结束.')
save_wave_file(FILEPATH, my_buf)
stream.close()
然后是获取token
import requests
import base64 #百度语音要求对本地语音二进制数据进行base64编码
#组装url获取token,详见文档
base_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=%s&client_secret=%s"
APIKey = "LZAdqHUGC********mbfKm"
SecretKey = "WYPPwgHu********BU6GM*****"
HOST = base_url % (APIKey, SecretKey)
def getToken(host):
res = requests.post(host)
return res.json()['access_token']
#传入语音二进制数据,token
#dev_pid为百度语音识别提供的几种语言选择
def speech2text(speech_data, token, dev_pid=1537):
FORMAT = 'wav'
RATE = '16000'
CHANNEL = 1
CUID = '********'
SPEECH = base64.b64encode(speech_data).decode('utf-8')
data = {
'format': FORMAT,
'rate': RATE,
'channel': CHANNEL,
'cuid': CUID,
'len': len(speech_data),
'speech': SPEECH,
'token': token,
'dev_pid':dev_pid
}
url = 'https://vop.baidu.com/server_api'
headers = {'Content-Type': 'application/json'}
# r=requests.post(url,data=json.dumps(data),headers=headers)
print('正在识别...')
r = requests.post(url, json=data, headers=headers)
Result = r.json()
if 'result' in Result:
return Result['result'][0]
else:
return Result
最后就是对返回的结果进行匹配,这里使用webbrowser
这个模块
webbrower.open(url)
完整demo
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Date : 2018-12-02 19:04:55
import wave
import requests
import time
import base64
from pyaudio import PyAudio, paInt16
import webbrowser
framerate = 16000 # 采样率
num_samples = 2000 # 采样点
channels = 1 # 声道
sampwidth = 2 # 采样宽度2bytes
FILEPATH = 'speech.wav'
base_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=%s&client_secret=%s"
APIKey = "********"
SecretKey = "************"
HOST = base_url % (APIKey, SecretKey)
def getToken(host):
res = requests.post(host)
return res.json()['access_token']
def save_wave_file(filepath, data):
wf = wave.open(filepath, 'wb')
wf.setnchannels(channels)
wf.setsampwidth(sampwidth)
wf.setframerate(framerate)
wf.writeframes(b''.join(data))
wf.close()
def my_record():
pa = PyAudio()
stream = pa.open(format=paInt16, channels=channels,
rate=framerate, input=True, frames_per_buffer=num_samples)
my_buf = []
# count = 0
t = time.time()
print('正在录音...')
while time.time() < t + 4: # 秒
string_audio_data = stream.read(num_samples)
my_buf.append(string_audio_data)
print('录音结束.')
save_wave_file(FILEPATH, my_buf)
stream.close()
def get_audio(file):
with open(file, 'rb') as f:
data = f.read()
return data
def speech2text(speech_data, token, dev_pid=1537):
FORMAT = 'wav'
RATE = '16000'
CHANNEL = 1
CUID = '*******'
SPEECH = base64.b64encode(speech_data).decode('utf-8')
data = {
'format': FORMAT,
'rate': RATE,
'channel': CHANNEL,
'cuid': CUID,
'len': len(speech_data),
'speech': SPEECH,
'token': token,
'dev_pid':dev_pid
}
url = 'https://vop.baidu.com/server_api'
headers = {'Content-Type': 'application/json'}
# r=requests.post(url,data=json.dumps(data),headers=headers)
print('正在识别...')
r = requests.post(url, json=data, headers=headers)
Result = r.json()
if 'result' in Result:
return Result['result'][0]
else:
return Result
def openbrowser(text):
maps = {
'百度': ['百度', 'baidu'],
'腾讯': ['腾讯', 'tengxun'],
'网易': ['网易', 'wangyi']
}
if text in maps['百度']:
webbrowser.open_new_tab('https://www.baidu.com')
elif text in maps['腾讯']:
webbrowser.open_new_tab('https://www.qq.com')
elif text in maps['网易']:
webbrowser.open_new_tab('https://www.163.com/')
else:
webbrowser.open_new_tab('https://www.baidu.com/s?wd=%s' % text)
if __name__ == '__main__':
flag = 'y'
while flag.lower() == 'y':
print('请输入数字选择语言:')
devpid = input('1536:普通话(简单英文),1537:普通话(有标点),1737:英语,1637:粤语,1837:四川话\n')
my_record()
TOKEN = getToken(HOST)
speech = get_audio(FILEPATH)
result = speech2text(speech, TOKEN, int(devpid))
print(result)
if type(result) == str:
openbrowser(result.strip(','))
flag = input('Continue?(y/n):')
经测试,大吼效果更佳