语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr
   * h* L/ X$ O$ X6 s9 s4 W% P
2. 
   ; `# ^' g# Z0 Z! |: Q
3. recognizer = sr.Recognizer()# }/ O9 q1 u6 x# `; T8 K
   
4. 
     N& a2 J7 f( a5 B( `! x$ h
5. with sr.Microphone() as source:6 m+ K/ e- [- ^& B1 \6 M0 @
   
6.     print("请说些什么：")* p- d* @( E9 s  O5 i; a  C
   
7.     audio = recognizer.listen(source)9 s+ }4 `% W$ N, ^7 F
   
8. . `- d$ P% q\" B/ L+ k3 O2 W
   
9.     try:5 c5 J. C% k7 \( R! ]: V
   
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))
    0 u6 F2 M, u1 i5 B% a5 K' A
11.     except sr.UnknownValueError:
    ( X7 ~2 }% h& ]' k4 P
12.         print("无法理解你的话")) D9 A# \4 P. v* S' b
    
13.     except sr.RequestError as e:
    2 ]3 S\" w5 c1 b, X\" c
14.         print("请求错误; {0}".format(e))2 }! X1 V( n7 |( k: d
    
15. 9 o% B6 a# Q) g* w\" S7 T7 }3 \7 c
    

复制代码

* G. b( v( W* j8 ~+ @4 @* e! y