语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr) F* a' k( Q/ S\" m2 ?
   
2. 4 C; a* [& f6 R8 @+ M
   
3. recognizer = sr.Recognizer()
   \" {% R3 x- g' ^7 u/ g1 K9 Y8 N0 h
4. # J! w, y- {0 B& U1 @) w\" n; ^
   
5. with sr.Microphone() as source:
     I: O! i$ t6 y
6.     print("请说些什么：")$ |3 W3 A) ?+ k5 d* ]' p; b9 `
   
7.     audio = recognizer.listen(source)
   ) D0 ?$ a4 l8 X. Q
8. & h: q+ X0 J\" _; x5 P# f
   
9.     try:; c( b2 l3 Z% i
   
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))
    # z6 o( I$ H+ T$ P\" [1 v
11.     except sr.UnknownValueError:
    * M/ R5 C1 R) j
12.         print("无法理解你的话")+ H# O& L) E6 A# \/ O' {, w
    
13.     except sr.RequestError as e:$ _* v0 X: n% \
    
14.         print("请求错误; {0}".format(e)); h# L! Y, [1 Z; {9 T5 j  r
    
15. 
    $ p8 ]& n: c  _' J3 b. F0 p

复制代码

" G8 m& K: B( l7 n