Python使用pyaudio实现录音功能

import pyaudio,wave
import numpy as np
def listen():
    temp = 20
    CHUNK = 1024
    FORMAT = pyaudio.paInt16
    CHANNELS = 1
    RATE = 16000
    RECORD_SECONDS = 2
    WAVE_OUTPUT_FILENAME = 'test.wav'

    mindb=2000    #最小声音，大于则开始录音，否则结束
    delayTime=1.3  #小声1.3秒后自动终止
    p = pyaudio.PyAudio()
    stream = p.open(format=FORMAT,
                    channels=CHANNELS,
                    rate=RATE,
                    input=True,
                    frames_per_buffer=CHUNK)
    #snowboydecoder.play_audio_file()
    print("开始!计时")

    frames = []
    flag = False            # 开始录音节点
    stat = True				#判断是否继续录音
    stat2 = False			#判断声音小了

    tempnum = 0				#tempnum、tempnum2、tempnum3为时间
    tempnum2 = 0

    while stat:
        data = stream.read(CHUNK,exception_on_overflow = False)
        frames.append(data)
        audio_data = np.frombuffer(data, dtype=np.short)
        temp = np.max(audio_data)
        if temp > mindb and flag==False:
            flag =True
            print("开始录音")
            tempnum2=tempnum

        if flag:

            if(temp < mindb and stat2==False):
                stat2 = True
                tempnum2 = tempnum
                print("声音小，且之前是是大的或刚开始，记录当前点")
            if(temp > mindb):
                stat2 =False
                tempnum2 = tempnum
                #刷新

            if(tempnum > tempnum2 + delayTime*15 and stat2==True):
                print("间隔%.2lfs后开始检测是否还是小声"%delayTime)
                if(stat2 and temp < mindb):
                    stat = False
                    #还是小声，则stat=True
                    print("小声！")
                else:
                    stat2 = False
                    print("大声！")


        print(str(temp)  +  "      " +  str(tempnum))
        tempnum = tempnum + 1
        if tempnum > 150:				#超时直接退出
            stat = False
    print("录音结束")

    stream.stop_stream()
    stream.close()
    p.terminate()
    wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()

listen()

import pyaudio
import numpy as np
from scipy import fftpack
import wave
# 录音
# 录音必须安装portaudio模块，否则会报错
# http://portaudio.com/docs/v19-doxydocs/compile_linux.html
def recording(filename, time=0, threshold=7000):
"""
:param filename: 文件名
:param time: 录音时间,如果指定时间，按时间来录音，默认为自动识别是否结束录音
:param threshold: 判断录音结束的阈值
:return:
"""
CHUNK = 1024 # 块大小
FORMAT = pyaudio.paInt16 # 每次采集的位数
CHANNELS = 1 # 声道数
RATE = 16000 # 采样率：每秒采集数据的次数
RECORD_SECONDS = time # 录音时间
WAVE_OUTPUT_FILENAME = filename # 文件存放位置
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK)
print("* 录音中...")
frames = []
if time > 0:
    for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
        data = stream.read(CHUNK)
        frames.append(data)
        else:
            stopflag = 0
            stopflag2 = 0
            while True:
                data = stream.read(CHUNK)
                rt_data = np.frombuffer(data, np.dtype('
# print(rt_data*10)
# 傅里叶变换
fft_temp_data = fftpack.fft(rt_data, rt_data.size, overwrite_x=True)
fft_data = np.abs(fft_temp_data)[0:fft_temp_data.size // 2 + 1]
# 测试阈值，输出值用来判断阈值
print(sum(fft_data) // len(fft_data))
# 判断麦克风是否停止，判断说话是否结束，# 麦克风阈值，默认7000
if sum(fft_data) // len(fft_data) > threshold:
    stopflag += 1
    else:
        stopflag2 += 1
        oneSecond = int(RATE / CHUNK)
        if stopflag2 + stopflag > oneSecond:
            if stopflag2 > oneSecond // 3 * 2:
            break
            else:
                stopflag2 = 0
                stopflag = 0
                frames.append(data)
                print("* 录音结束")
                stream.stop_stream()
                stream.close()
                p.terminate()
                with wave.open(WAVE_OUTPUT_FILENAME, 'wb') as wf:
                    wf.setnchannels(CHANNELS)
                    wf.setsampwidth(p.get_sample_size(FORMAT))
                    wf.setframerate(RATE)
                    wf.writeframes(b''.join(frames))
                    # recording('ppp.mp3', time=5) # 按照时间来录音，录音5秒
                    recording('ppp.mp3') # 没有声音自动停止，自动停止