语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr
   ; [  P2 v5 x% _/ S; z5 C/ j. s% J
2. 
   ( r' e- G: }' t- H, \
3. recognizer = sr.Recognizer()& d2 h, O9 U: G/ G; ^
   
4. 
   3 j7 D, l' U  Z
5. with sr.Microphone() as source:6 ~1 Z- O: B$ r1 y1 l/ f
   
6.     print("请说些什么：")
   * a5 Y* I, {# i3 {
7.     audio = recognizer.listen(source)
   9 p7 a% t/ w. a- K
8. 
   * @2 d9 d& m+ t8 |4 G\" M
9.     try:
   # J! x* B8 j! ]5 p
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))! N3 d7 Z, P( p8 e
    
11.     except sr.UnknownValueError:  N! _& p5 }$ X5 |
    
12.         print("无法理解你的话")
    : ~& ~% y) E5 I+ U
13.     except sr.RequestError as e:- f9 ]$ T5 ?- k2 |8 U2 ~
    
14.         print("请求错误; {0}".format(e))& `: L! k% d1 e) H7 B* R
    
15. 0 m\" E2 a\" K7 ~4 x$ S- w# S- g7 t
    

复制代码