webrtcvad模块使用

最近在实现一个功能的时候，用到了webrtc模块的vad部分的python版本，因参考的原博客找不到链接了，为了方便自己以后查阅相关内容，故整理成博客供日后方便。接下来开始正题，当然了，要想使用这个webrtcvad，自然就是安装它了，命令也很简单。

pip install webrtcvad

关于该包的使用，github上有提供一个example.py，可以参照该example.py文件使用webrtcvad。网址为https://github.com/wiseman/py-webrtcvad/blob/master/example.py。 不过该代码运行的结果是切分后的片段。接下来整理的是将vad后的片段整个保存。下面是整个代码,相关参数的含义可以查看webrtcvad的文档。

import contextlib
import wave
import webrtcvad
import os
import sys
import collections
MODE = 3 
def read_wave(path):
    """Reads a .wav file.
    Takes the path, and returns (PCM audio data, sample rate).
    """
    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, 48000)
        pcm_data = wf.readframes(wf.getnframes())
        return pcm_data, sample_rate
def write_wave(path, audio, sample_rate):
    """Writes a .wav file.
    Takes path, PCM audio data, and 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):
    """Represents a "frame" of audio data."""
    def __init__(self, bytes, timestamp, duration):
        self.bytes = bytes
        self.timestamp = timestamp
        self.duration = duration

def frame_generator(frame_duration_ms, audio, sample_rate):
    """Generates audio frames from PCM audio data.
    Takes the desired frame duration in milliseconds, the PCM data, and
    the sample rate.
    Yields Frames of the requested duration.
    """
    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, vad, frames):

    voiced_frames = []
    for idx, frame in enumerate(frames):
        is_speech = vad.is_speech(frame.bytes, sample_rate)
        if is_speech:
            voiced_frames.append(frame)
    return b''.join(f.bytes for f in voiced_frames)

def voiced_frames_expand(voiced_frames, duration=2):
    total = duration * 16000
    expand_voiced_frames = voiced_frames
    while len(expand_voiced_frames) < total:
        expand_num = total - len(expand_voiced_frames)
        expand_voiced_frames += voiced_frames[: expand_num]
    return expand_voiced_frames
def filter(wavpath, out_dir, expand=False):
    audio, sample_rate = read_wave(wavpath)
    vad = webrtcvad.Vad(MODE)
    frames = frame_generator(30, audio, sample_rate)
    frames = list(frames)
    voiced_frames = vad_collector(sample_rate, vad, frames)
    voiced_frames = voiced_frames_expand(voiced_frames, 2)
    wav_name = wavpath.split('\')[-1]
    save_path = out_dir + '\'  +"mo"+wav_name
    write_wave(save_path, voiced_frames, sample_rate)

if __name__ == "__main__":
    in_wave = 'C:\Users\ctw\code\DiveintoDeep\1B356F62.wav'
    outwav='C:\Users\ctw\code\DiveintoDeep\'
    filter(in_wave, outwav, expand=False)

上面代码是在windows平台上运行的，如果在linux下运行，则相应的文件路径需要改变，且函数filter中的wav_name和save_path里的\要修改成/

下面来看看效果，原语音的波形如下

去除vad后的波形如下,效果还是可以的。