语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr
   5 Z: D4 @+ K8 r: @0 W& I
2. 9 V9 H$ r3 l9 e+ d
   
3. recognizer = sr.Recognizer()- N' C0 W3 R# F* \8 |7 ~
   
4. 
   6 R4 U9 \5 E! |% _0 p) p' \& P
5. with sr.Microphone() as source:
   / K3 P* @' s5 D0 f) a$ l
6.     print("请说些什么：")
   7 S# \5 M. E$ y2 t8 h' g
7.     audio = recognizer.listen(source)
   ! v& E4 z; O\" _' L/ P6 h6 `0 v
8. % |. y* J  `& c' Q
   
9.     try:$ Z- N' B  F) v. J7 c% i
   
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))& f8 C6 [6 _5 p2 l7 q
    
11.     except sr.UnknownValueError:4 L9 P0 K/ K$ ?0 V& \
    
12.         print("无法理解你的话")% W  a* v1 E8 ~1 A6 ^
    
13.     except sr.RequestError as e:( x& I& R5 G) w. ?& z$ o& n! `
    
14.         print("请求错误; {0}".format(e))1 e0 q. v* [\" c# q% A
    
15. 7 i# R8 S: c' C. D% Z
    

复制代码

- }3 C9 `: U) U  G2 Y