zoukankan      html  css  js  c++  java
  • 语音活性检测器py-webrtcvad安装使用

    谷歌为WebRTC项目开发的VAD是目前最优秀、最先进和免费的产品之一。webrtcvad是WebRTC语音活动检测器(VAD)的python接口。兼容python2和python3。功能是将一段音频数据分为静音与非静音。它对于电话和语音识别很有用。

    1、安装pip

    yum -y install epel-release
    yum -y install python-pip

    2、安装webrtcvad

    yum -y install python-devel
    pip install webrtcvad

    3、webrtcvad测试脚本(test_webrtcvad.py

    import collections
    import contextlib
    import sys
    import wave
     
    import webrtcvad
     
     
    def read_wave(path):
        with contextlib.closing(wave.open(path, 'rb')) as wf:
            num_channels = wf.getnchannels()
            assert num_channels == 1
            sample_width = wf.getsampwidth()
            assert sample_width == 2
            sample_rate = wf.getframerate()
            assert sample_rate in (8000, 16000, 32000)
            pcm_data = wf.readframes(wf.getnframes())
            return pcm_data, sample_rate
     
     
    def write_wave(path, audio, sample_rate):
        with contextlib.closing(wave.open(path, 'wb')) as wf:
            wf.setnchannels(1)
            wf.setsampwidth(2)
            wf.setframerate(sample_rate)
            wf.writeframes(audio)
     
     
    class Frame(object):
        def __init__(self, bytes, timestamp, duration):
            self.bytes = bytes
            self.timestamp = timestamp
            self.duration = duration
     
     
    def frame_generator(frame_duration_ms, audio, sample_rate):
        n = int(sample_rate * (frame_duration_ms / 1000.0) * 2)
        offset = 0
        timestamp = 0.0
        duration = (float(n) / sample_rate) / 2.0
        while offset + n < len(audio):
            yield Frame(audio[offset:offset + n], timestamp, duration)
            timestamp += duration
            offset += n
     
     
    def vad_collector(sample_rate, frame_duration_ms,
                      padding_duration_ms, vad, frames):
        num_padding_frames = int(padding_duration_ms / frame_duration_ms)
        ring_buffer = collections.deque(maxlen=num_padding_frames)
        triggered = False
        voiced_frames = []
        for frame in frames:
            sys.stdout.write(
                '1' if vad.is_speech(frame.bytes, sample_rate) else '0')
            if not triggered:
                ring_buffer.append(frame)
                num_voiced = len([f for f in ring_buffer
                                  if vad.is_speech(f.bytes, sample_rate)])
                if num_voiced > 0.9 * ring_buffer.maxlen:
                    sys.stdout.write('+(%s)' % (ring_buffer[0].timestamp,))
                    triggered = True
                    voiced_frames.extend(ring_buffer)
                    ring_buffer.clear()
            else:
                voiced_frames.append(frame)
                ring_buffer.append(frame)
                num_unvoiced = len([f for f in ring_buffer
                                    if not vad.is_speech(f.bytes, sample_rate)])
                if num_unvoiced > 0.9 * ring_buffer.maxlen:
                    sys.stdout.write('-(%s)' % (frame.timestamp + frame.duration))
                    triggered = False
                    yield b''.join([f.bytes for f in voiced_frames])
                    ring_buffer.clear()
                    voiced_frames = []
        if triggered:
            sys.stdout.write('-(%s)' % (frame.timestamp + frame.duration))
        sys.stdout.write('
    ')
        if voiced_frames:
            yield b''.join([f.bytes for f in voiced_frames])
     
     
    def main(args):
        if len(args) != 2:
            sys.stderr.write(
                'Usage: example.py <aggressiveness> <path to wav file>
    ')
            sys.exit(1)
        audio, sample_rate = read_wave(args[1])
        vad = webrtcvad.Vad(int(args[0]))
        frames = frame_generator(30, audio, sample_rate)
        frames = list(frames)
        segments = vad_collector(sample_rate, 30, 300, vad, frames)
        for i, segment in enumerate(segments):
            #path = 'chunk-%002d.wav' % (i,)
            print('--end')
            #write_wave(path, segment, sample_rate)
     
     
    if __name__ == '__main__':
        main(sys.argv[1:])

    4、运行命令(其中,第一个参数为敏感系数,取值0-3,越大表示越敏感,越激进,对细微的声音频段都可以识别出来;第二个参数为wav文件存放路径,目前仅支持8K,16K,32K的采样率,示例wav文件下载:73.wav 链接:https://pan.baidu.com/s/19YJB9u0zvCFGBLDRisK1KQ 密码:fgkf)

    [root@host-10-0-251-159 ~]# python test_webrtcvad.py 2 /home/73.wav
    00000000000000000000000000000000000000000000000000000000000000000000000000111111+(2.1)11111111111111111111111100000000-(3.36)--end
    00000000000111111+(3.57)1111111111111111111111111111111111111001111111111111111111111111111111111111000000111111111111111111111111111111111111111111111111101111111111110000011110000000111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111000111111111111111111111111111100111111111111111111111111111111111111111111111100000000000011100000000-(14.43)--end
    000000000000000000000000000000000000011+(15.3)111100000001110000-(16.14)--end
    00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000001111111+(21.21)11111111111111111111111110000000-(22.47)--end
    00000000000111111+(22.68)111111111111111111111111111111111111111111100000000000-(24.6)--end
    000000111111+(24.66)111111111111111111111111111111111111111111111111111110000000-(26.76)--end
    1111111111+(26.76)1111111111111110000000000-(27.81)--end
    000000001111+(27.87)11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111100000-(31.38)--end
    0001111111+(31.38)11111111111111111110111111111111111000000-(32.91)--end
    00000001111111111111+(33.21)111000111111111111111111111111111111111110000000000-(35.04)--end
    000000000000000000000000000111111+(35.73)111111111111111111111111111111111111111111111111111000011111111111111111111111111000000011111111111111111111111111111111111111111111111111111111111111111111111111111000011100000000-(41.43)--end
    000000000000000000000000000000000000000000000111111+(42.66)1111111111111111111110000000-(43.8)--end
    000000001111111+(43.95)1111111111111111111111110011111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111010000000-(51.03)--end
    00000000111111+(51.15)1111111111111111111111111111111111111001111111111111111111111111111111111000000-(53.82)--end
    0111111111+(53.82)11111111111111111111111111111111111111111111000011111111111111111111111111001111111111111111111111111111111111111111111111111111000111111111111111111111111111111111111111111111111111110000000-(59.85)--end
    00000000000000000000000000111111+(60.51)11111111111111111111111111111111111000000111100111111111111111111111111111111111111111111111111111111111111111111111110011100000000-(64.74)--end
    0000111000000000000000000001111111+(65.46)11111111111111111111111111111110011100000000000000-(67.26)--end
    00000000111000000000111111+(67.74)111111111111111111111111111111111000100000000-(69.39)--end
    00001111111+(69.42)11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111100001111111111110001111111111111111111111111111111110000000-(74.55)--end
    1111111111+(74.55)111111111111111111111111111111111111100000011111011111111111111111111111111111111111111111111111111111111111111111111111111111111111100111111111111111111111111111111111111111111111111111111111111111111111000000000-(81.24)--end
    0011111000000111111+(81.51)111111111111111111111111111111111111111111111111111111111111111111111100000000111111111111111111111111111111111111111111111111111111111111111001111111111111111111111111111111111000000001100000000-(87.66)--end
    000000000001111111+(87.9)1111111111111111111111111111110111111000001100000000-(89.76)--end
    000000000000000000000000000000000000000000000000111111+(91.08)1111111111111100000000-(92.04)--end
    0000000000000111111+(92.31)11111111111111110111011111111111111111111111110001111111111111111111111111111111111111111000001111111111111111111111111111111111111111100000000-(96.9)--end
    000000000000000111111+(97.23)11111111111111111111111111111111111111100111111001111111111111111111111111111111111111111111111111001111111111111111111111111111111111111111100000000000000000-(102.27)--end
    000111000000111111+(102.51)111111111111111111111111111111111111111111111110000000-(104.43)--end
    0000111111+(104.43)111111111111111111111111111111110000000-(105.9)--end
    11100111100000000011111111+(106.38)111000000011111111111111111111111111111100000000-(108.12)--end
    00001111000000000011110111111+(108.69)111111111111111111111111111111110000000-(110.16)--end
    000000000000000000000000011100111000111111+(111.12)111111111111111111100001111111111111111111111111110000000-(113.13)--end
    0001111111+(113.13)111111111111111111111111111111111110000010000000-(114.87)--end
    0111011111+(114.87)1111111111111111111111111111111111100000011111111111111111111111111111111111111111111110110000000-(118.08)--end
    000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
  • 相关阅读:
    SpringBoot 项目发现的错误
    maven项目SpringBoot框架
    eclipse不能正常启动
    @Service、@Controller、@Repository、@Resource注解的作用
    navicat 不能正常启动
    序列化和反序列化
    hibernate主键生成策略
    eclipse 安装注意事项之一
    js-cookie的使用说明
    微信小程序自定义顶部导航栏,添加背景图,透明色等
  • 原文地址:https://www.cnblogs.com/zhenyuyaodidiao/p/9288455.html
Copyright © 2011-2022 走看看