Probabilistic Equalization Discovery for Audio Signals
Project description
Audio EQ Infer
audioeqinfer is a Python package for discovering audio equalization (EQ) curves of an altered signal through probabilistic inference about the signal source.
It supports both importance sampling and Metropolis-Hastings (MH) to infer flexible, data-driven EQ transformations from audio signals.
See examples notebook for usage examples.
Currently in beta.
Features
- Flexible spline-based parameterization of EQ curves
- Probabilistic inference using:
- Importance sampling
- Metropolis-Hastings
- Handles large audio files with online chunked processing
- Modular design with current set up for flow models (
f_X) - Clean API for inference and training
- Easily adjustable number of EQ parameters
Installation
This package is available on pypi
Requirements
- Python
- PyTorch
- torch
- nflows
- numpy
- scipy
- matplotlib
- statsmodels
- pedalboard
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file audioeqinfer-0.1.0.tar.gz.
File metadata
- Download URL: audioeqinfer-0.1.0.tar.gz
- Upload date:
- Size: 7.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3dd6763f9ea0657fcf548bbf1fdb2c6c3edc46e4de7f505d1dd6e796f560a983
|
|
| MD5 |
611c723fb3883f655545340cf9b5bd32
|
|
| BLAKE2b-256 |
c479948aa43210cf65fe739bf300cbd47e2a580eb452ebd09cddf2b12f26420a
|
File details
Details for the file audioeqinfer-0.1.0-py3-none-any.whl.
File metadata
- Download URL: audioeqinfer-0.1.0-py3-none-any.whl
- Upload date:
- Size: 8.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
380288bdd5283492193bc6ec45566b814d217699f16412d97a82027c53f72cf5
|
|
| MD5 |
e1ea46bb45b259330a1d8598b607e8ba
|
|
| BLAKE2b-256 |
963f63b68f082bdd2632432b98c987c2735c870a8071d1b5135ca0a008ef0d7c
|
