语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr
   2 l0 j8 I' s* t' C0 _* o) ^
2. * a4 F' v5 [9 k# W+ T5 R
   
3. recognizer = sr.Recognizer()' Y6 f4 F' u/ b  P
   
4. 
   5 ~% S; m, K+ b; N3 G5 {# U
5. with sr.Microphone() as source:
   . d4 m' y2 x. x' S) j
6.     print("请说些什么：")
   . \- a- P8 R, [$ `+ k6 @' p  `4 y
7.     audio = recognizer.listen(source)
   4 E, a, m$ `3 g- W% \
8. 
   ! l9 y) J! f7 N\" ?8 O' ^( w+ i% i- ]
9.     try:4 d7 y% I* u* _2 K; ^
   
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))
    9 f\" x# I1 x, D& Z$ t
11.     except sr.UnknownValueError:$ I8 k& g9 J6 S9 l
    
12.         print("无法理解你的话")0 R\" [- M$ H* M2 M/ {, D
    
13.     except sr.RequestError as e:# ?/ J9 r8 p4 h% o
    
14.         print("请求错误; {0}".format(e))
    % m* l! I) J2 e. K\" R! e
15. 
    ) e0 X% q  M7 `9 ]2 J( L% K

复制代码

, q8 S+ L( J; N* M9 u/ U8 Z7 ~/ x