Skip to content

Latest commit

 

History

History
30 lines (22 loc) · 1 KB

README.md

File metadata and controls

30 lines (22 loc) · 1 KB

GANsynth-pytorch

A simplified PyTorch implementation of GANsynth from magenta. Some of the codes are borrowed from magenta orginal repo.

Note

This repo only support the best setting in the GANsynth paper which is a simple version comparing to orginal Tensorflow version by magenta team. So if you want to test other frequency setting, you may need to modify the code.

Prepare Data

Use Make Training Data notebook to generate HDF5 file for training.

Train a new model

You have to make a directory to save model checkpint and output spectrum first.

    python3 train.py

Inference

Use Inference notebook to load the model and generate audio.

Example Generated Audio

https://drive.google.com/open?id=1tNnOtcqCpgTTXGmkHJBA4K6MalBjdsPC

Reference