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 d* R! W8 `9 V& c# W  V
2. 
   , t3 ]& A) N6 p  H1 x- B1 ~; u% O
3. recognizer = sr.Recognizer()
   . @. Y8 T! `0 [
4. ! [\" u, ~3 u5 E
   
5. with sr.Microphone() as source:
   $ j) f4 O$ j* T) u* a1 B1 J! \3 |
6.     print("请说些什么：")+ P3 c6 |  ~+ R\" G% Z0 U8 P
   
7.     audio = recognizer.listen(source)
   * I) l1 Q* R0 b8 P' u\" C. |7 R
8. 8 q+ D. `; ?6 O4 L/ N0 @
   
9.     try:+ t\" e6 J) Z; t1 V- I: i5 M& J
   
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))
    , C# ?  Y1 W0 g- w: _* ~
11.     except sr.UnknownValueError:8 m8 I+ H1 K  ^5 ?\" \& z
    
12.         print("无法理解你的话")9 \$ F3 p  ~  n3 ^/ `
    
13.     except sr.RequestError as e:: ?! ~% ^+ B& l\" [& D5 G
    
14.         print("请求错误; {0}".format(e))
    , [1 U; z* z+ R- i; @
15. \" D/ p) m$ P4 D+ p2 V# c6 C
    

复制代码