Generate a micmon spectrum dataset from a set of raw labelled audio files

micmon_datagen_example.py

import os

from micmon.audio import AudioDirectory, AudioPlayer, AudioFile
from micmon.dataset import DatasetWriter

basedir = os.path.expanduser('~/datasets/sound-detect')
audio_dir = os.path.join(basedir, 'audio')
datasets_dir = os.path.join(basedir, 'data')
cutoff_frequencies = [250, 2500]

# Scan the base audio_dir for labelled audio samples
audio_dirs = AudioDirectory.scan(audio_dir)

# Save the spectrum information and labels of the samples to a
# different compressed file for each audio file.
for audio_dir in audio_dirs:
    dataset_file = os.path.join(datasets_dir, os.path.basename(audio_dir.path) + '.npz')
    print(f'Processing audio sample {audio_dir.path}')

    with AudioFile(audio_dir) as reader, \
            DatasetWriter(dataset_file,
                          low_freq=cutoff_frequencies[0],
                          high_freq=cutoff_frequencies[1]) as writer:
        for sample in reader:
            writer += sample