语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr
   \" q2 ~! q  G9 F: W  ~* s
2. % Y& b% E& S4 M
   
3. recognizer = sr.Recognizer()
   ( u7 Y0 m5 x3 J7 H1 P
4. $ \) d, |3 s+ O\" s% f% p
   
5. with sr.Microphone() as source:
   1 B/ @* U3 _' t
6.     print("请说些什么：")
   & x0 g+ `3 ?. w\" d# H3 @
7.     audio = recognizer.listen(source)( V4 z* W7 C\" m* X8 O; n
   
8. 
   5 I4 }' G* W* M6 e: L( F
9.     try:# Q5 z: F/ w! s. R! {7 |/ p
   
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))# c\" G# c9 {- @, a
    
11.     except sr.UnknownValueError:+ B' _6 p) w, q. _$ Z, `/ n
    
12.         print("无法理解你的话")' v1 i4 F6 H4 b$ U
    
13.     except sr.RequestError as e:\" X) B6 B% u4 J4 |
    
14.         print("请求错误; {0}".format(e))
    9 z) t+ u\" H0 P; U0 W, G6 x
15. ( d  M; F8 ^$ x5 n
    

复制代码

6 I0 Y6 B* |' v  o' w0 F