语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr
   * P( ^4 p5 E) O\" W! g- N
2. 3 j& B# @0 N' r; S
   
3. recognizer = sr.Recognizer()- \3 B* C* G1 z$ m* @( T1 G
   
4. 
   6 ~3 t4 {# S. t& @1 P/ q\" I# y
5. with sr.Microphone() as source:! O2 l/ [/ n6 M$ ]: L
   
6.     print("请说些什么：")( }' ]1 Z5 a& V8 N% l, e/ z
   
7.     audio = recognizer.listen(source)
   $ \0 F& h! M2 d/ E& K  |
8. 
     @6 M# @- \+ f
9.     try:
   ! |7 {. d0 |3 {* E\" Y( d, c
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN')), N% m; _4 w6 T4 H
    
11.     except sr.UnknownValueError:
    6 r  Z+ r9 X\" \' E3 t5 Y
12.         print("无法理解你的话")
    . {+ t6 K  d4 z  y! j7 `
13.     except sr.RequestError as e:
    0 m/ o/ A& ~  a0 E6 S
14.         print("请求错误; {0}".format(e))- c# M* u\" _' A% T
    
15. 
    , P- t5 f, V$ s3 c

复制代码

7 T0 e/ G7 f7 ~1 o' U