NeMo HiFiGAN Model

In this example, we show how to optimize NeMo HiFiGAN model. We recommend running this example in NVIDIA NGC PyTorch container.

Installation

1. Install model_navigator and pre-requisites

2. Install Riva dependencies

sudo apt-get install -y libsndfile1 ffmpeg
python3 -m pip install git+https://github.com/NVIDIA/NeMo.git@r1.7.2#egg=nemo_toolkit[all]

Usage

To run the example, simply run the optimize.py script:

./optimize.py --output-path tts_hifigan.nav