archinetai/cqt-pytorch
An invertible and differentiable implementation of the Constant-Q Transform (CQT).
This tool helps audio engineers and researchers analyze sound by converting raw audio waveforms into a frequency-time representation called a Constant-Q Transform (CQT) spectrogram. It takes an audio signal as input and produces a detailed visual map showing how different frequencies change over time. Users can also convert this spectrogram back into the original audio. This is ideal for those working with audio analysis, music information retrieval, or sound processing.
No commits in the last 6 months. Available on PyPI.
Use this if you need to precisely understand the frequency content of an audio signal over time, especially for musical or acoustic analysis, and potentially reconstruct the original audio from this analysis.
Not ideal if you are looking for a simple, pre-trained audio classification model or a general-purpose audio player.
Stars
72
Forks
4
Language
Python
License
MIT
Last pushed
Dec 09, 2022
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/archinetai/cqt-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Naresh1318/Adversarial_Autoencoder
A wizard's guide to Adversarial Autoencoders
mseitzer/pytorch-fid
Compute FID scores with PyTorch.
acids-ircam/RAVE
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
ratschlab/aestetik
AESTETIK: Convolutional autoencoder for learning spot representations from spatial...
jaanli/variational-autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)