语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr
   / b9 t- A3 i! g1 b5 r. K
2. 
   ! ~/ L! W% Q) [
3. recognizer = sr.Recognizer(). _8 c1 Y$ m+ w  A
   
4. ) [% ~; d% a) x9 J+ e\" Q1 f. t& ^
   
5. with sr.Microphone() as source:1 i1 K9 o5 G9 {& x4 Z! x/ d  V6 i  o3 ~
   
6.     print("请说些什么：")
   \" A6 P  s2 m( A, W
7.     audio = recognizer.listen(source)2 f. ?# m/ `7 n9 {& l' {
   
8. 
   : j# U. X4 X% I' o% I/ S; V
9.     try:
   + v3 \: m9 r5 G4 M. t) x% G! I6 v\" |
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))
    . f, N& O' K# V
11.     except sr.UnknownValueError:
    2 m0 J2 `6 ~- {6 ]8 q# q\" i
12.         print("无法理解你的话"): l& x7 v' L$ d7 ^
    
13.     except sr.RequestError as e:9 B8 d' {% P. k: g* S2 L  M4 `
    
14.         print("请求错误; {0}".format(e))6 u& j- U+ R( m
    
15. 
    0 f1 y& R+ _4 Y9 m7 J\" n! A

复制代码

7 Z" H; J! U+ f1 U9 x; I) H