https://github.com/cyrusvahidi/non-linear-fx
Keras/TF Reimplementation of Modelling non-linear audio effects with end-to-end deep learning (Marco Martinez)
https://github.com/cyrusvahidi/non-linear-fx
Last synced: about 1 month ago
JSON representation
Keras/TF Reimplementation of Modelling non-linear audio effects with end-to-end deep learning (Marco Martinez)
- Host: GitHub
- URL: https://github.com/cyrusvahidi/non-linear-fx
- Owner: cyrusvahidi
- Created: 2019-10-02T11:08:55.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2022-11-22T04:40:50.000Z (over 2 years ago)
- Last Synced: 2025-03-31T22:23:22.194Z (3 months ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 779 KB
- Stars: 7
- Watchers: 3
- Forks: 2
- Open Issues: 13
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Reimplementation of Modeling Nonlinear Audio Effects with End-to-end Deep Neural Networks
Experimental implementation of [Modeling Nonlinear Audio Effects with End-to-end Deep Neural Networks.](https://ieeexplore.ieee.org/abstract/document/8683529/) [Original work](https://github.com/mchijmma/DL-AFx) by [Marco Martínez](https://github.com/mchijmma)
# Notice
This repository is incomplete. It was a reimplementation before the release of Marco's journal paper and accompanying code for all of the end-to-end analog audio effect models: https://github.com/mchijmma/DL-AFx
### TODO
- Smooth Adaptive Activation Function (SAAF) - with an adaptive tanh on the backend this model produces artefacts.
## Requirements
`Python 3.6.6`
`CUDNN`
`keras 2.1.6`
`tensorflow-gpu 1.12.0`
## bash config
For a consisent environment configuration, add the following to your `~/.bashrc`
```
module load python/3.6.6
export PATH=${PATH}:/usr/local/cuda-10.0/bin
export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/cuda-10.0/lib64
module load cuda/10.0-cudnn7.4.2
export CUDA_VISIBLE_DEVICES=0
```
-------------- WIP --------------