archinetai/archisound
A collection of pre-trained audio models, in PyTorch.
ArchiSound provides pre-trained models for working with audio. You can input raw stereo audio at 48kHz and get a highly compressed representation, or reconstruct audio from these compressed versions. This is useful for researchers and developers building new audio applications or analyzing sound data efficiently.
116 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to compress high-quality stereo audio into a much smaller digital footprint while retaining the ability to reconstruct it, or if you're experimenting with audio generation and manipulation.
Not ideal if you need perfectly lossless audio compression or if your primary goal is simple audio playback without advanced processing.
Stars
116
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jan 27, 2023
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/archinetai/archisound"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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.