语音识别——CUM_Sphinx的安装及使用

CUM Sphinx

注意：
语言模型的构建看此篇帖子：https://blog.youkuaiyun.com/qq_29894613/article/details/93667263
本人的Linux系统为Ubuntu18.04。

1. 安装SpeechRecognitio模块

   pip3 install SpeechRecognition  # python3.0+
   

   验证SpeechRecognition模块是否安装成功

   import speech_recognition as sr 
   print(sr.__version__)
   

2. 安装PocketSphinx及依附模块

   来源：https://github.com/Uberi/speech_recognition/blob/master/reference/pocketsphinx.rst，在该链接的Building PocketSphinx-Python from source部分

• On any Debian-derived Linux distributions (like Ubuntu and Mint):
  1. Run sudo apt-get install python python-all-dev python-pip build-essential swig git libpulse-dev libasound2-dev for Python 2, or sudo apt-get install python3 python3-all-dev python3-pip build-essential swig git libpulse-dev libasound2-dev for Python 3.
  2. Run pip install pocketsphinx for Python 2, or pip3 install pocketsphinx for Python 3.

3. 测试是否成功

   import speech_recognition as sr
   
   # 读入本地".wav"格式的音频文件
   r = sr.Recognizer()
   harvard = sr.AudioFile('harvard.wav')
   
   # 通过麦克风输入音频（安装过Microphone模块后才可使用）
   # 安装链接：https://github.com/Uberi/speech_recognition
   # with sr.Microphone() as source:
   #     print("Say something!")
   #     audio = r.listen(source)
   
    with harvard as source:
        audio = r.record(source)
   # 调用Sphinx模块识别音频文件中的语言
   try:
       print("Sphinx thinks you said " + r.recognize_sphinx(audio))
       # 将结果保存到文本文件
      	txtName = 'savedSpeechRecognition.txt'
       with open(txtName, 'w+') as f:
           lines = f.readlines()  # 读取所有行数据
        f.write(r.recognize_sphinx(audio))
           f.write('\n')
   except sr.UnknownValueError:
       print("Sphinx could not understand audio")
   except sr.RequestError as e:
       print("Sphinx error; {0}".format(e))