Detecting Silence in Python Voice Assistant

Question

I'm making small pet-project. It's voice assistant. Now, development is on speech recognition part, and i need to make silent detection, to react on user's phrase end. I use vosk for speech recognition, pyaudio to record audio, numpy for energy calculations, and wave to save output file. Here is a part of my code:

import vosk
import json
import pyaudio
import numpy as np
import wave

def is_silence(audio_chunk, silence_thresh=-50, energy_thresh=0.001):
    # Convert the audio chunk to a NumPy array of 16-bit integers
    audio_chunk = np.frombuffer(audio_chunk, dtype=np.int16)

    # Calculate the energy of the audio chunk
    energy = np.sum(audio_chunk.astype(np.float32) ** 2) / float(len(audio_chunk))

    # Check if both energy and maximum absolute value are below thresholds
    return energy < energy_thresh and np.max(np.abs(audio_chunk)) < silence_thresh

def record_audio(output_file, max_silence_duration=1500, sample_rate=16000, chunk_size=1024, silence_thresh=-50):
    # Initialize PyAudio
    p = pyaudio.PyAudio()

    # Open a stream for recording audio
    stream = p.open(format=pyaudio.paInt16,
                    channels=1,
                    rate=sample_rate,
                    input=True,
                    frames_per_buffer=chunk_size)

    # Initialize variables for storing audio frames and counting consecutive silence
    frames = []
    consecutive_silence_counter = 0

    print("Recording...")

    while True:
        # Read a chunk of audio data from the stream
        data = stream.read(chunk_size)
        frames.append(data)

        # Convert the audio chunk to a NumPy array
        audio_chunk = np.frombuffer(data, dtype=np.int16)

        # Check if the audio chunk is silence
        if is_silence(audio_chunk, silence_thresh=silence_thresh):
            consecutive_silence_counter += 1
        else:
            consecutive_silence_counter = 0

        # Break the loop if consecutive silence reaches the specified duration
        if consecutive_silence_counter * chunk_size >= (max_silence_duration // chunk_size):
            break

    print("Recording finished.")

    # Stop and close the audio stream, and terminate PyAudio
    stream.stop_stream()
    stream.close()
    p.terminate()

    # Write the recorded frames to a WAV file
    with wave.open(output_file, 'wb') as wf:
        wf.setnchannels(1)
        wf.setsampwidth(p.get_sample_size(pyaudio.paInt16))
        wf.setframerate(sample_rate)
        wf.writeframes(b''.join(frames))

# recognize_speech function

if __name__ == "__main__":
    # Path to the Vosk model
    model_path = "path/to/vosk-model-en-us-0.22-lgraph"
    
    # Path to the output audio file
    output_file_path = "path to audio file"
    
    # Record audio and save it to the specified output file
    audio_data = record_audio(output_file=output_file_path)
    
    # Recognize speech from the recorded audio using the Vosk model
    recognized_text = recognize_speech(model_path, audio_data)

    # Print the recognized text
    print("Recognized text:", recognized_text)

My question is why is_silence method returns False, even if i saying nothing. I have background noises, but they are not so loud. I already tried using pydub and webrtcvad, but they didn't work. It's not a problem with file saving, or speech recognition. I know that i need to edit is_silence method or while cycle in record_audio function, but i just haven't got any ideas how to make this. I run it on MacOS and in python 3.12 virtual environment.

I already tried using pydub, webrtcvad, pyttsx3, and pocketsphinx, but they don't work. I tried to edit some arguments to a methods like energy_thresh and silence_thresh, too. Any ideas to do this?