FFTNet
A PyTorch implementation of the FFTNet: a Real-Time Speaker-Dependent Neural Vocoder
Quick Start:
Install requirements:
pip install -r requirements.txt
Download dataset:
wget http://festvox.org/cmu_arctic/cmu_arctic/packed/cmu_us_slt_arctic-0.95-release.tar.bz2
tar xf cmu_us_slt_arctic-0.95-release.tar.bz2
Extract features:
python preprocess.py
Training with default hyperparams:
python train.py
Synthesize from model:
python generate.py --checkpoint=/path/to/model --lc_file=/path/to/local_conditon
TODO:
Notes:
This is not offical implementation, some details are different from the paper.
Now the generated speech from this repo is not so good as wavenet vocoder.
Work in progress.