Domain-specific generation of test inputs for robustness testing of ML models
Project description
insynth
Testing Audio Perturbators
from insynth.perturbators.audio import AudioShortNoisePerturbator
import librosa
from scipy.io.wavfile import write
perturbator = ...
signal, sr=librosa.load(file_name, sr=None)
result = perturbator.apply((signal, sr))
write("output.wav", sr, result)
License
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
insynth-0.0.1.tar.gz
(3.6 kB
view hashes)
