语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr
   8 {# V9 f, e' E5 ~# E; N! Y8 A
2. 4 v6 h4 A& z$ k\" j. c4 l( M5 R
   
3. recognizer = sr.Recognizer()
   2 z/ _\" t1 ?3 t
4. , f% F8 N) S1 l
   
5. with sr.Microphone() as source:
   + Y. o& v( ^: `* M) `7 k. s) n6 e
6.     print("请说些什么：")8 c/ F8 Z& @4 }9 {+ t
   
7.     audio = recognizer.listen(source)
   5 L0 u& f1 `2 T- G9 R
8. 5 p. y0 I$ p+ E8 a/ H0 |
   
9.     try:
   8 S( C) V- Q, t! n/ d! d4 p: ~
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))) E4 @/ H, j( F7 @7 C/ C
    
11.     except sr.UnknownValueError:
    9 k9 i) C3 R& n0 R) J' a
12.         print("无法理解你的话")
    ' ^8 T6 C# F! z
13.     except sr.RequestError as e:
    ) Q0 s\" ?# t) Z2 z
14.         print("请求错误; {0}".format(e))( C  b; U/ H  @/ C! b9 K  F3 P
    
15. : U6 y% j7 X# o; _! |; I9 |
    

复制代码

$ K* A4 u9 \& i! u# W: ]