webrtcvad | vad wraper on webrtcvad | Machine Learning library

Delimiting words is out of the audio domain and requires a kind of intelligence. Doing it manually is easy because we are intelligent and know exactly what we are looking for, but automatizing the process is hard because, as you already noticed, a silence is not (not only, not always) a word delimiter.

At audio level, we can only approach a solution and this require both analyzing the amplitude of the signal and adding some time mechanisms. As an example, Protools provides a nice tool named Strip Silence that cuts audio regions automatically based on the amplitude of the signal. It always keeps the material at its original position in the timeline and naturally each region knows its own duration. In addition to the threshold in dB, and to prevent creating too much regions, it provides several useful parameters in the time domain : a minimum length for the created regions, a delay before the cut (the delay is computed from the point the amplitude passes below the threshold), an inverted delay before reopening the gate (the delay is computed backward from the point the amplitude passes above the threshold).

This could be a good starting point for you. Implementing such a system probably won't be 100 % successful, but you could obtain a quite good ratio if the settings are well adjusted to the speaker. Even if it's not perfect, it will significantly reduce the need for manual work.

py-webrtcvad, expects the audio data to be 16bit PCM little-endian - as is the most common storage format in WAV files.

librosa and its underlying I/O library pysoundfile however always returns floating point arrays in the range [-1.0, 1.0]. To convertt this to bytes containing 16bit PCM you can use the following float_to_pcm16 function.

And I have tested to use the read_pcm16 function a direct replacement of read_wave in the official py-webrtcvad example. But allowing to open any audio file supported by soundfile (WAV, FLAC, OGG) etc.

Similar problem appeared when I was trying to install some other software. Searching for solution I came accross this issue. Running the following 2 commands solved the issue for both problems:

After

w.rewind()

I tried

len(w.readframes(0))

0

Which is different from your results, where you got 1.

Interestingly however,

len(w.readframes(1))

2

But this makes sense, in a convoluted fashion, since there are indeed 2 bytes. (16bit audio frames imply that there are 2 bytes per frame. Since you are calling len on a binary object, I think it therefore makes sense that it would return the number of actual bytes.)

If you want to work on your audio data, perhaps you should investigate a library like numpy to do further analysis or processing of your audio.

import numpy as np

c = np.frombuffer(w.readframes(w.getnframes()), dtype="int16")

c.shape

(178175,)

c[0] = 100

c[1] = 122

c[100] = -132

This is the raw waveform data. It is on the range of (-2^15, 2^15) or, -32768 to 32,768. Since the first portion of your audio file is quiet at the beginning, small values in the first few hundred frames makes good sense.