Re: How to properly use py-webrtcvad?

marc nicole <mk1853387@gmail.com> wrote or quoted:

return _webrtcvad.process(self._vad, sample_rate, buf, length)

Error: Error while processing frame

  (I was not able to check the following tips myself!
  So, please read them as a mere wild guess!)

  That error you're running into - it's possibly because the
  audio format webrtcvad wants isn't jiving with what you're
  feeding it. Let me break it down for you:

  WebRTC VAD is picky about its audio, like a foodie at a farmers
  market:

  - It wants 16-bit mono PCM, nothing fancy

  - Sample rates got to be 8000, 16000, 32000, or 48000 Hz

  - Frame durations should be 10, 20, or 30 ms, like clockwork

  Tweak your PyAudio setup like you're fine-tuning a classic car:

  Python

self.FORMAT = pyaudio.paInt16
self.CHANNELS = 1
self.RATE = 16000
self.FRAMES_PER_BUFFER = 480  # 30 ms at 16000 Hz, smooth as a SoCal highway

    Give your audio reading loop a makeover:

  Python

for i in range(0, int(self.RATE / self.FRAMES_PER_BUFFER * self.RECORD_SECONDS)):
    data = self.stream.read(self.FRAMES_PER_BUFFER)
    is_speech = self.vad.is_speech(data, self.RATE)

  Make sure your audio data is on point:

  Python

import numpy as np

# Turn that audio data into a numpy array, like magic
audio_array = np.frombuffer(data, dtype=np.int16)

# If it's not mono, make it mono - no stereo allowed at this party
if self.CHANNELS > 1:
    audio_array = audio_array[::self.CHANNELS]

# Back to bytes it goes
audio_bytes = audio_array.tobytes()

is_speech = self.vad.is_speech(audio_bytes, self.RATE)

  Crank up that VAD aggressiveness:

  Python

self.vad = webrtcvad.Vad(3)  # 3 is as aggressive as LA traffic

  (Just remember to adjust your sample rate and frame duration
  to fit your needs.)