hubertsiuzdak/snac
Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate
This project helps audio engineers and researchers significantly compress audio while maintaining quality. It takes raw audio files, like music or speech, and converts them into very small digital codes. These codes can then be used to reconstruct the audio at a much lower file size, making it easier to store or transmit.
752 stars. Used by 3 other packages. No commits in the last 6 months. Available on PyPI.
Use this if you need to compress audio into discrete tokens at a very low bitrate, especially for applications like audio generation or efficient storage.
Not ideal if you require multi-channel (stereo or surround) audio support, as current models only support single-channel (mono) audio.
Stars
752
Forks
43
Language
Python
License
MIT
Category
Last pushed
Nov 19, 2024
Commits (30d)
0
Dependencies
4
Reverse dependents
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hubertsiuzdak/snac"
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.