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.
- July 2019: fairseq relicensed under MIT license
- July 2019: RoBERTa models and code release
- June 2019: wav2vec models and code release
- April 2019: fairseq demo paper @ NAACL 2019
Fairseq provides reference implementations of various sequence-to-sequence models, including:
- Convolutional Neural Networks (CNN)
- Language Modeling with Gated Convolutional Networks (Dauphin et al., 2017)
- Convolutional Sequence to Sequence Learning (Gehring et al., 2017)
- Classical Structured Prediction Losses for Sequence to Sequence Learning (Edunov et al., 2018)
- Hierarchical Neural Story Generation (Fan et al., 2018)
- wav2vec: Unsupervised Pre-training for Speech Recognition (Schneider et al., 2019)
- LightConv and DynamicConv models
- 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)
- Understanding Back-Translation at Scale (Edunov et al., 2018)
- Adaptive Input Representations for Neural Language Modeling (Baevski and Auli, 2018)
- Mixture Models for Diverse Machine Translation: Tricks of the Trade (Shen et al., 2019)
- RoBERTa: A Robustly Optimized BERT Pretraining Approach (Liu et al., 2019)
Additionally:
- multi-GPU (distributed) training on one machine or across multiple machines
- fast generation on both CPU and GPU with multiple search algorithms implemented:
- beam search
- Diverse Beam Search (Vijayakumar et al., 2016)
- sampling (unconstrained, top-k and top-p/nucleus)
- large mini-batch training even on a single GPU via delayed updates
- mixed precision training (trains faster with less GPU memory on NVIDIA tensor cores)
- extensible: easily register new models, criterions, tasks, optimizers and learning rate schedulers
We also provide pre-trained models for several benchmark translation and language modeling datasets.
- PyTorch version >= 1.0.0
- Python version >= 3.5
- For training new models, you'll also need an NVIDIA GPU and NCCL
Please follow the instructions here to install PyTorch: https://github.com/pytorch/pytorch#installation.
If you use Docker make sure to increase the shared memory size either with
--ipc=host or --shm-size as command line options to nvidia-docker run.
After PyTorch is installed, you can install fairseq with pip:
pip install fairseq
On MacOS,
CFLAGS="-stdlib=libc++" pip install fairseq
Installing from source
To install fairseq from source and develop locally:
git clone https://github.com/pytorch/fairseq
cd fairseq
pip install --editable .
Improved training speed
Training speed can be further improved by installing NVIDIA's
apex library with the --cuda_ext option.
fairseq will automatically switch to the faster modules provided by apex.
The full documentation contains instructions for getting started, training new models and extending fairseq with new model types and tasks.
We provide pre-trained models and pre-processed, binarized test sets for several tasks listed below, as well as example training and evaluation commands.
- Translation: convolutional and transformer models are available
- Language Modeling: convolutional models are available
We also have more detailed READMEs to reproduce results from specific papers:
- RoBERTa: A Robustly Optimized BERT Pretraining Approach (Liu et al., 2019)
- wav2vec: Unsupervised Pre-training for Speech Recognition (Schneider et al., 2019)
- Mixture Models for Diverse Machine Translation: Tricks of the Trade (Shen et al., 2019)
- Pay Less Attention with Lightweight and Dynamic Convolutions (Wu et al., 2019)
- Understanding Back-Translation at Scale (Edunov et al., 2018)
- Classical Structured Prediction Losses for Sequence to Sequence Learning (Edunov et al., 2018)
- Hierarchical Neural Story Generation (Fan et al., 2018)
- Scaling Neural Machine Translation (Ott et al., 2018)
- Convolutional Sequence to Sequence Learning (Gehring et al., 2017)
- Language Modeling with Gated Convolutional Networks (Dauphin et al., 2017)
- Facebook page: https://www.facebook.com/groups/fairseq.users
- Google group: https://groups.google.com/forum/#!forum/fairseq-users
fairseq(-py) is MIT-licensed. The license applies to the pre-trained models as well.
Please cite as:
@inproceedings{ott2019fairseq,
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},
}