/spec2spec

A machine learning audio timbre transfer model based on pix2pix.

Primary LanguageJupyter Notebook

spec2spec

Spectrogram-to-spectrogram translation based on pix2pix.

Description

This repository contains all the files related to the spec2spec project, including a web demo and training notebooks. The source of the web demo is in /backend and /frontend, while training files reside under /training.

Specifically, /frontend contains files for the frontend web interface, while /backend contains files for the backend processing.

More readme may be found in each subfolder containing more explanation of each corresponding components.