MIT License Latest Release Build Status Documentation Status

Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks. We provide reference implementations of various sequence modeling papers:

List of implemented papers

- **Convolutional Neural Networks (CNN)** - [Language Modeling with Gated Convolutional Networks (Dauphin et al., 2017)](examples/language_model/conv_lm/ - [Convolutional Sequence to Sequence Learning (Gehring et al., 2017)](examples/conv_seq2seq/ - [Classical Structured Prediction Losses for Sequence to Sequence Learning (Edunov et al., 2018)]( - [Hierarchical Neural Story Generation (Fan et al., 2018)](examples/stories/ - [wav2vec: Unsupervised Pre-training for Speech Recognition (Schneider et al., 2019)](examples/wav2vec/ - **LightConv and DynamicConv models** - [Pay Less Attention with Lightweight and Dynamic Convolutions (Wu et al., 2019)](examples/pay_less_attention_paper/ - **Long Short-Term Memory (LSTM) networks** - Effective Approaches to Attention-based Neural Machine Translation (Luong et al., 2015) - **Transformer (self-attention) networks** - Attention Is All You Need (Vaswani et al., 2017) - [Scaling Neural Machine Translation (Ott et al., 2018)](examples/scaling_nmt/ - [Understanding Back-Translation at Scale (Edunov et al., 2018)](examples/backtranslation/ - [Adaptive Input Representations for Neural Language Modeling (Baevski and Auli, 2018)](examples/language_model/transformer_lm/ - [Mixture Models for Diverse Machine Translation: Tricks of the Trade (Shen et al., 2019)](examples/translation_moe/ - [RoBERTa: A Robustly Optimized BERT Pretraining Approach (Liu et al., 2019)](examples/roberta/ - [Facebook FAIR's WMT19 News Translation Task Submission (Ng et al., 2019)](examples/wmt19/ - [Jointly Learning to Align and Translate with Transformer Models (Garg et al., 2019)](examples/joint_alignment_translation/ ) - [Multilingual Denoising Pre-training for Neural Machine Translation (Liu et at., 2020)](examples/mbart/ - [Neural Machine Translation with Byte-Level Subwords (Wang et al., 2020)](examples/byte_level_bpe/ - **Non-autoregressive Transformers** - Non-Autoregressive Neural Machine Translation (Gu et al., 2017) - Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement (Lee et al. 2018) - Insertion Transformer: Flexible Sequence Generation via Insertion Operations (Stern et al. 2019) - Mask-Predict: Parallel Decoding of Conditional Masked Language Models (Ghazvininejad et al., 2019) - [Levenshtein Transformer (Gu et al., 2019)](examples/nonautoregressive_translation/

What's New:


We also provide pre-trained models for translation and language modeling with a convenient torch.hub interface:

en2de = torch.hub.load('pytorch/fairseq', 'transformer.wmt19.en-de.single_model')
en2de.translate('Hello world', beam=5)
# 'Hallo Welt'

See the PyTorch Hub tutorials for translation and RoBERTa for more examples.

Requirements and Installation

on MacOS:

CFLAGS="-stdlib=libc++" pip install --editable ./

* **For faster training** install NVIDIA's [apex]( library:
git clone
cd apex
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" \
  --global-option="--deprecated_fused_adam" --global-option="--xentropy" \
  --global-option="--fast_multihead_attn" ./

Getting Started

The full documentation contains instructions for getting started, training new models and extending fairseq with new model types and tasks.

Pre-trained models and examples

We provide pre-trained models and pre-processed, binarized test sets for several tasks listed below, as well as example training and evaluation commands.

We also have more detailed READMEs to reproduce results from specific papers:

Join the fairseq community


fairseq(-py) is MIT-licensed. The license applies to the pre-trained models as well.


Please cite as:

  title = {fairseq: A Fast, Extensible Toolkit for Sequence Modeling},
  author = {Myle Ott and Sergey Edunov and Alexei Baevski and Angela Fan and Sam Gross and Nathan Ng and David Grangier and Michael Auli},
  booktitle = {Proceedings of NAACL-HLT 2019: Demonstrations},
  year = {2019},