语音识别的Python案例一

2744557306

基本的语音到文本

1. import speech_recognition as sr' c! }/ G$ N: @% S
   
2. 6 D! d5 Z. _* o. S( O
   
3. recognizer = sr.Recognizer()
   7 m8 u- c0 k$ t) g& C4 X, O
4. 
   \" s+ i9 n( l+ t+ {. X* |, Y/ X8 R
5. with sr.Microphone() as source:
   1 N$ y' x4 ?* K5 j0 K. q# m
6.     print("请说些什么：")9 u3 c- M. j- O
   
7.     audio = recognizer.listen(source)
   . y1 g) D5 X' N6 i
8. 
   5 ~9 R& [' X$ |- V
9.     try:! S2 C) G* d* p' i, b
   
10.         print("你说的是：" + recognizer.recognize_google(audio, language='zh-CN'))- Q3 q: T$ l* w3 j/ h
    
11.     except sr.UnknownValueError:+ ?- Q9 j5 s+ M% d9 J% G
    
12.         print("无法理解你的话")& }! s5 u1 I( J& w: D9 B
    
13.     except sr.RequestError as e:
    \" n+ R- _0 T' d4 q
14.         print("请求错误; {0}".format(e))
    ' w/ k\" a1 B9 w2 z: l5 t! Z
15. 
    * i$ X! t- @# ]

复制代码

2 n: @' Y, w* I0 x