Installation

Basics

First install Python >= 3.5, PyTorch >=v.0.4.1 and git.

Create and activate a virtual environment to install the package into:

$ python3 -m venv jnmt
$ source jnmt/bin/activate

Cloning

Then clone JoeyNMT from GitHub and switch to its root directory:

(jnmt)$ git clone https://github.com/joeynmt/joeynmt.git
(jnmt)$ cd joeynmt

Installing JoeyNMT

Install JoeyNMT and it’s requirements:

(jnmt)$ pip3 install .

Run the unit tests to make sure your installation is working:

(jnmt)$ python3 -m unittest

Warning! When running on GPU you need to manually install the suitable PyTorch version for your [CUDA](https://developer.nvidia.com/cuda-zone) version. This is described in the [PyTorch installation instructions](https://pytorch.org/get-started/locally/).

You’re ready to go!