Spijkervet/torchaudio-augmentations
Audio transformations library for PyTorch
This tool helps machine learning engineers working with audio data to easily create many varied versions of original sound files. You provide original audio recordings, and it outputs multiple stochastically transformed audio examples. It's for anyone training machine learning models that need robust audio data, such as for speech recognition, sound event detection, or music classification.
236 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to artificially expand your audio dataset with diverse, transformed versions of existing recordings to improve your machine learning model's performance.
Not ideal if you need to perform precise, non-randomized audio edits for production or artistic purposes, as its focus is on stochastic augmentation for model training.
Stars
236
Forks
28
Language
Python
License
MIT
Category
Last pushed
Apr 19, 2022
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Spijkervet/torchaudio-augmentations"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.