python的pyaudio可以进行录音，播放，生成wav文件等等,WAVE是录音时用的标准的WINDOWS文件格式，文件的扩展名为WAV，数据本身的格式为PCM或压缩型，属于无损音乐格式的一种。在我们研究语音识别，自然语言处理的过程中，常常会使用到它，比如我们调用百度语音识别所以我们首先研究一下pyaudio库的安装与使用。
安装：
pipinstall pyaudio
调用pyaudio使用麦克风录制声音：
#!/usr/bin/python3# -*- coding: utf-8 -*-from pyaudio import PyAudio, paInt16 import numpy as np from datetime import datetime import waveclass recoder:NUM_SAMPLES = 2000#pyaudio内置缓冲大小SAMPLING_RATE = 8000 #取样频率LEVEL = 500 #声音保存的阈值COUNT_NUM = 20#NUM_SAMPLES个取样之内出现COUNT_NUM个大于LEVEL的取样则记录声音SAVE_LENGTH = 8 #声音记录的最小长度：SAVE_LENGTH * NUM_SAMPLES 个取样TIME_COUNT = 60#录音时间，单位sVoice_String = []def savewav(self,filename):wf = wave.open(filename, 'wb') wf.setnchannels(1) wf.setsampwidth(2) wf.setframerate(self.SAMPLING_RATE) wf.writeframes(np.array(self.Voice_String).tostring()) # wf.writeframes(self.Voice_String.decode())wf.close() def recoder(self):pa = PyAudio() stream = pa.open(format=paInt16, channels=1, rate=self.SAMPLING_RATE, input=True, frames_per_buffer=self.NUM_SAMPLES) save_count = 0 save_buffer = [] time_count = self.TIME_COUNTwhile True:time_count -= 1# print time_count# 读入NUM_SAMPLES个取样string_audio_data = stream.read(self.NUM_SAMPLES) # 将读入的数据转换为数组audio_data = np.fromstring(string_audio_data, dtype=np.short)# 计算大于LEVEL的取样的个数large_sample_count = np.sum( audio_data > self.LEVEL )print(np.max(audio_data))# 如果个数大于COUNT_NUM，则至少保存SAVE_LENGTH个块if large_sample_count > self.COUNT_NUM:save_count = self.SAVE_LENGTH else: save_count -= 1if save_count < 0:save_count = 0 if save_count > 0 : # 将要保存的数据存放到save_buffer中#print save_count > 0 and time_count >0save_buffer.append( string_audio_data ) else: #print save_buffer# 将save_buffer中的数据写入WAV文件，WAV文件的文件名是保存的时刻#print "debug"if len(save_buffer) > 0 : self.Voice_String = save_buffersave_buffer = [] print("Recode a piece of voice successfully!")return Trueif time_count==0: if len(save_buffer)>0:self.Voice_String = save_buffersave_buffer = [] print("Recode a piece of voice successfully!")return Trueelse:return Falseif __name__ == "__main__":r = recoder()r.recoder()r.savewav("test.wav")
pyaudio文档：http://people.csail.mit.edu/hubert/pyaudio/docs/
参考文档：/yexiaohhjk/article/details/73132562
