语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr
   6 C+ U  t9 U4 _* j
2. 
   4 W4 M. j+ i  l) _) N+ L8 {
3. recognizer = sr.Recognizer(), v! }+ p% P2 `7 x7 l# X0 O
   
4. 
   $ V  p( k, K# M& R\" F6 z5 q
5. with sr.Microphone() as source:7 t0 k5 ]0 F* A* K9 M) J5 C
   
6.     print("请说些什么：")
   3 x8 G\" r\" A/ \8 o4 p$ C
7.     audio = recognizer.listen(source)
   3 |/ ~. p/ U6 Q3 i
8. 
   . k5 G; }: f6 g. S/ R
9.     try:7 B! b/ j: \) [, B6 q
   
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))
    - f% S; R5 @6 J+ x; U! h
11.     except sr.UnknownValueError:
    ) g' r: K\" p# F
12.         print("无法理解你的话")\" C- E* t# ?& g& e
    
13.     except sr.RequestError as e:& ^; L  i' e' q# K* L+ X- o
    
14.         print("请求错误; {0}".format(e))  k7 f6 ~% U3 K. y, T5 y
    
15. 6 s/ |; ]3 J' R# W4 O& X
    

复制代码