Awesome Open Source
Awesome Open Source

  Joey-NMT Joey NMT

build License

Goal and Purpose

🐨 Joey NMT framework is developed for educational purposes. It aims to be a clean and minimalistic code base to help novices find fast answers to the following questions.

  • ❔ How to implement classic NMT architectures (RNN and Transformer) in PyTorch?
  • ❔ What are the building blocks of these architectures and how do they interact?
  • ❔ How to modify these blocks (e.g. deeper, wider, ...)?
  • ❔ How to modify the training procedure (e.g. add a regularizer)?

In contrast to other NMT frameworks, we will not aim for the most recent features or speed through engineering or training tricks since this often goes in hand with an increase in code complexity and a decrease in readability. 👀

However, Joey NMT re-implements baselines from major publications.

Check out the detailed documentation and our paper.


Joey NMT was initially developed and is maintained by Jasmijn Bastings (University of Amsterdam) and Julia Kreutzer (Heidelberg University), now both at Google Research. Mayumi Ohta at Heidelberg University is continuing the legacy.

Welcome to our new contributors ♥️, please don't hesitate to open a PR or an issue if there's something that needs improvement!


Joey NMT implements the following features (aka the minimalist toolkit of NMT 🔧):

  • Recurrent Encoder-Decoder with GRUs or LSTMs
  • Transformer Encoder-Decoder
  • Attention Types: MLP, Dot, Multi-Head, Bilinear
  • Word-, BPE- and character-based tokenization
  • BLEU, ChrF evaluation
  • Beam search with length penalty and greedy decoding
  • Customizable initialization
  • Attention visualization
  • Learning curve plotting
  • Scoring hypotheses and references


Joey NMT is built on PyTorch. Please make sure you have a compatible environment. We tested Joey NMT v2.2 with

  • python 3.10
  • torch 1.13.1
  • cuda 11.6

⚠️ Warning When running on GPU you need to manually install the suitable PyTorch version for your CUDA version. For example, you can install PyTorch 1.13.1 with CUDA v11.6 as follows:

$ pip install --upgrade torch==1.13.1 --extra-index-url

See PyTorch installation instructions.

You can install Joey NMT either A. via pip or B. from source.

A. Via pip (the latest stable version)

$ pip install joeynmt

B. From source (for local development)

  1. Clone this repository:
$ git clone
$ cd joeynmt
  1. Install Joey NMT and it's requirements:
$ pip install -e .
  1. Run the unit tests:
$ python -m unittest

Change logs


  • compatibility with torch 1.13 tested
  • torchhub introduced
  • bugfixes, minor refactoring
previous releases


  • upgrade to python 3.10, torch 1.12
  • replace Automated Mixed Precision from NVIDA's amp to Pytorch's amp package
  • replace with pycord in the Discord Bot demo
  • data iterator refactoring
  • add wmt14 ende / deen benchmark trained on v2 from scratch
  • add tokenizer tutorial
  • minor bugfixes

v2.0 Breaking change!

  • upgrade to python 3.9, torch 1.11
  • torchtext.legacy dependencies are completely replaced by
  • joeynmt/ handles tokenization internally (also supports bpe-dropout!)
  • joeynmt/ loads data from plaintext, tsv, and huggingface's datasets
  • scripts/ trains subwords, creates joint vocab
  • enhancement in decoding
    • scoring with hypotheses or references
    • repetition penalty, ngram blocker
    • attention plots for transformers
  • yapf, isort, flake8 introduced
  • bugfixes, minor refactoring

⚠️ Warning The models trained with Joey NMT v1.x can be decoded with Joey NMT v2.0. But there is no guarantee that you can reproduce the same score as before.


  • upgrade to sacrebleu 2.0, python 3.7, torch 1.8
  • bugfixes


  • upgrade to torchtext 0.9 (torchtext -> torchtext.legacy)
  • n-best decoding
  • demo colab notebook


  • Multi-GPU support
  • fp16 (half precision) support

Documentation & Tutorials

We also updated the documentation thoroughly for Joey NMT 2.0!

For details, follow the tutorials in notebooks dir.




⚠️ Warning For Joey NMT v1.x, please refer the archive here.

Joey NMT has 3 modes: train, test, and translate, and all of them takes a YAML-style config file as argument. You can find examples in the configs directory. transformer_small.yaml contains a detailed explanation of configuration options.

Most importantly, the configuration contains the description of the model architecture (e.g. number of hidden units in the encoder RNN), paths to the training, development and test data, and the training hyperparameters (learning rate, validation frequency etc.).

📝 Info Note that subword model training and joint vocabulary creation is not included in the 3 modes above, has to be done separately. We provide a script that takes care of it: scritps/

$ python scripts/ configs/transformer_small.yaml --joint

train mode

For training, run

$ python -m joeynmt train configs/transformer_small.yaml

This will train a model on the training data, validate on validation data, and store model parameters, vocabularies, validation outputs. All needed information should be specified in the data, training and model section of the config file (here configs/transformer_small.yaml).

 *.ckpt          # checkpoints
 *.hyps          # translated texts at validation
 config.yaml     # config file
 spm.model       # sentencepiece model / subword-nmt codes file
 src_vocab.txt   # src vocab
 trg_vocab.txt   # trg vocab
 train.log       # train log
 validation.txt  # validation scores

💡 Tip Be careful not to overwrite model_dir, set overwrite: False in the config file.

test mode

This mode will generate translations for validation and test set (as specified in the configuration) in model_dir/out.[dev|test].

$ python -m joeynmt test configs/transformer_small.yaml --ckpt model_dir/avg.ckpt

If --ckpt is not specified above, the checkpoint path in load_model of the config file or the best model in model_dir will be used to generate translations.

You can specify i.e. sacrebleu options in the test section of the config file.

💡 Tip scripts/ will generate averaged checkpoints for you.

$ python scripts/ --inputs model_dir/*00.ckpt --output model_dir/avg.ckpt

If you want to output the log-probabilities of the hypotheses or references, you can specify return_score: 'hyp' or return_score: 'ref' in the testing section of the config. And run test with --output_path and --save_scores options.

$ python -m joeynmt test configs/transformer_small.yaml --ckpt model_dir/avg.ckpt --output_path model_dir/pred --save_scores

This will generate model_dir/pred.{dev|test}.{scores|tokens} which contains scores and corresponding tokens.

📝 Info

  • If you set return_score: 'hyp' with greedy decoding, then token-wise scores will be returned. The beam search will return sequence-level scores, because the scores are summed up per sequence during beam exploration.
  • If you set return_score: 'ref', the model looks up the probabilities of the given ground truth tokens, and both decoding and evaluation will be skipped.
  • If you specify n_best >1 in config, the first translation in the nbest list will be used in the evaluation.

translate mode

This mode accepts inputs from stdin and generate translations.

  • File translation

    $ python -m joeynmt translate configs/transformer_small.yaml < my_input.txt > output.txt
  • Interactive translation

    $ python -m joeynmt translate configs/transformer_small.yaml

    You'll be prompted to type an input sentence. Joey NMT will then translate with the model specified in --ckpt or the config file.

    💡 Tip Interactive translate mode doesn't work with Multi-GPU. Please run it on single GPU or CPU.

Benchmarks & pretrained models

wmt14 ende / deen

We trained the models with JoeyNMT v2.1.0 from scratch.
cf) wmt14 deen leaderboard in paperswithcode

Direction Architecture tok dev test #params download
en->de Transformer sentencepiece 24.36 24.38 60.5M wmt14_ende.tar.gz (766M)
de->en Transformer sentencepiece 30.60 30.51 60.5M wmt14_deen.tar.gz (766M)

sacrebleu signature: nrefs:1|case:mixed|eff:no|tok:13a|smooth:exp|version:2.2.0

⚠️ Warning The following models are trained with JoeynNMT v1.x, and decoded with Joey NMT v2.0. See config_v1.yaml and config_v2.yaml in the linked zip, respectively. Joey NMT v1.x benchmarks are archived here.

iwslt14 deen

Pre-processing with Moses decoder tools as in this script.

Direction Architecture tok dev test #params download
de->en RNN subword-nmt 31.77 30.74 61M rnn_iwslt14_deen_bpe.tar.gz (672MB)
de->en Transformer subword-nmt 34.53 33.73 19M transformer_iwslt14_deen_bpe.tar.gz (221MB)

sacrebleu signature: nrefs:1|case:lc|eff:no|tok:13a|smooth:exp|version:2.0.0

📝 Info For interactive translate mode, you should specify pretokenizer: "moses" in the both src's and trg's tokenizer_cfg, so that you can input raw sentence. Then MosesTokenizer and MosesDetokenizer will be applied internally. For test mode, we used the preprocessed texts as input and set pretokenizer: "none" in the config.

Masakhane JW300 afen / enaf

We picked the pretrained models and configs (bpe codes file etc.) from

Direction Architecture tok dev test #params download
af->en Transformer subword-nmt - 57.70 46M transformer_jw300_afen.tar.gz (525MB)
en->af Transformer subword-nmt 47.24 47.31 24M transformer_jw300_enaf.tar.gz (285MB)

sacrebleu signature: nrefs:1|case:mixed|eff:no|tok:intl|smooth:exp|version:2.0.0

JParaCrawl enja / jaen

For training, we split JparaCrawl v2 into train and dev set and trained a model on them. Please check the preprocessing script here. We tested then on kftt test set and wmt20 test set, respectively.

Direction Architecture tok wmt20 kftt #params download
en->ja Transformer sentencepiece 17.66 14.31 225M jparacrawl_enja.tar.gz (2.3GB)
ja->en Transformer sentencepiece 14.97 11.49 221M jparacrawl_jaen.tar.gz (2.2GB)

sacrebleu signature:

  • en->ja nrefs:1|case:mixed|eff:no|tok:ja-mecab-0.996-IPA|smooth:exp|version:2.0.0
  • ja->en nrefs:1|case:mixed|eff:no|tok:intl|smooth:exp|version:2.0.0

Note: In wmt20 test set, newstest2020-enja has 1000 examples, newstest2020-jaen has 993 examples.


In order to keep the code clean and readable, we make use of:

  • Style checks:
    • pylint with (mostly) PEP8 conventions, see .pylintrc.
    • yapf, isort, and flake8; see .style.yapf, setup.cfg and Makefile.
  • Typing: Every function has documented input types.
  • Docstrings: Every function, class and module has docstrings describing their purpose and usage.
  • Unittests: Every module has unit tests, defined in test/unit/.

To ensure the repository stays clean, unittests and linters are triggered by github's workflow on every push or pull request to main branch. Before you create a pull request, you can check the validity of your modifications with the following commands:

$ make check
$ make test


Since this codebase is supposed to stay clean and minimalistic, contributions addressing the following are welcome:

  • code correctness
  • code cleanliness
  • documentation quality
  • speed or memory improvements
  • resolving issues
  • providing pre-trained models

Code extending the functionalities beyond the basics will most likely not end up in the main branch, but we're curious to learn what you used Joey NMT for.

Projects and Extensions

Here we'll collect projects and repositories that are based on Joey NMT, so you can find inspiration and examples on how to modify and extend the code.

Joey NMT v2.x

  • 👂 JoeyS2T. Joey NMT is extended for Speech-to-Text tasks! Checkout the code and the EMNLP 2022 Paper.
  • 🗯 Discord Joey. This script demonstrates how to deploy Joey NMT models as a Chatbot on Discord. Code

Joey NMT v1.x

  • 🕸 Masakhane Web. @CateGitau, @Kabongosalomon, @vukosim and team built a whole web translation platform for the African NMT models that Masakhane built with Joey NMT. The best is: it's completely open-source, so anyone can contribute new models or features. Try it out here, and check out the code.
  • ⚙️ MutNMT. @sjarmero created a web application to train NMT: it lets the user train, inspect, evaluate and translate with Joey NMT --- perfect for NMT newbies! Code here. The tool was developed by Prompsit in the framework of the European project MultiTraiNMT.
  • 🌟 Cantonese-Mandarin Translator. @evelynkyl trained different NMT models for translating between the low-resourced Cantonese and Mandarin, with the help of some cool parallel sentence mining tricks! Check out her work here.
  • 📖 Russian-Belarusian Translator. @tsimafeip built a translator from Russian to Belarusian and adapted it to legal and medical domains. The code can be found here.
  • 💪 Reinforcement Learning. @samuki implemented various policy gradient variants in Joey NMT: here's the code, could the logo be any more perfect? 💪 🐨
  • Sign Language Translation. @neccam built a sign language translator that continuosly recognizes sign language and translates it. Check out the code and the CVPR 2020 paper!
  • 🔤 @bpopeters built Possum-NMT for multilingual grapheme-to-phoneme transduction and morphologic inflection. Read their paper for SIGMORPHON 2020!
  • 📷 Image Captioning. @pperle and @stdhd built an image captioning tool on top of Joey NMT, check out the code and the demo!
  • 💡 Joey Toy Models. @bricksdont built a collection of scripts showing how to install Joey NMT, preprocess data, train and evaluate models. This is a great starting point for anyone who wants to run systematic experiments, tends to forget python calls, or doesn't like to run notebook cells!
  • 🌍 African NMT. @jaderabbit started an initiative at the Indaba Deep Learning School 2019 to "put African NMT on the map". The goal is to build and collect NMT models for low-resource African languages. The Masakhane repository contains and explains all the code you need to train Joey NMT and points to data sources. It also contains benchmark models and configurations that members of Masakhane have built for various African languages. Furthermore, you might be interested in joining the Masakhane community if you're generally interested in low-resource NLP/NMT. Also see the EMNLP Findings paper.
  • 💬 Slack Joey. Code to locally deploy a Joey NMT model as chat bot in a Slack workspace. It's a convenient way to probe your model without having to implement an API. And bad translations for chat messages can be very entertaining, too ;)
  • 🌐 Flask Joey. @kevindegila built a flask interface to Joey, so you can deploy your trained model in a web app and query it in the browser.
  • 👥 User Study. We evaluated the code quality of this repository by testing the understanding of novices through quiz questions. Find the details in Section 3 of the Joey NMT paper.
  • 📝 Self-Regulated Interactive Seq2Seq Learning. Julia Kreutzer and Stefan Riezler. Published at ACL 2019. Paper and Code. This project augments the standard fully-supervised learning regime by weak and self-supervision for a better trade-off of quality and supervision costs in interactive NMT.
  • 🐫 Hieroglyph Translation. Joey NMT was used to translate hieroglyphs in this IWSLT 2019 paper by Philipp Wiesenbach and Stefan Riezler. They gave Joey NMT multi-tasking abilities.

If you used Joey NMT for a project, publication or built some code on top of it, let us know and we'll link it here.


Please leave an issue if you have questions or issues with the code.

For general questions, email us at joeynmt <at> 💌


If you use Joey NMT in a publication or thesis, please cite the following paper:

    title = "Joey {NMT}: A Minimalist {NMT} Toolkit for Novices",
    author = "Kreutzer, Julia  and
      Bastings, Jasmijn  and
      Riezler, Stefan",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "",
    doi = "10.18653/v1/D19-3019",
    pages = "109--114",


Joeys are infant marsupials. 🐨

Related Awesome Lists
Top Programming Languages

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (891,361
Pytorch (22,655
Validation (20,400
Education (7,933
Attention (3,887
Seq2seq (1,367
Machine Translation (957
Nmt (522
Neural Machine Translation (224
Transformer Architecture (68
Rnn Pytorch (60
Pytorch Transformers (22
Seq2seq Pytorch (7
Joey Nmt (3