fairseq documentation

Fairseq is a sequence modeling toolkit written in PyTorch that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks.

Getting Started

• Evaluating Pre-trained Models
• Training a New Model
• Advanced Training Options
• Command-line Tools

Extending Fairseq

• Overview
• Tutorial: Simple LSTM
• Tutorial: Classifying Names with a Character-Level RNN

Library Reference

• Tasks
  • Translation
  • Language Modeling
  • Adding new tasks
• Models
  • Convolutional Neural Networks (CNN)
  • Long Short-Term Memory (LSTM) networks
  • Transformer (self-attention) networks
  • Adding new models
  • Incremental decoding
• Criterions
• Optimizers
• Learning Rate Schedulers
• Data Loading and Utilities
  • Datasets
  • Dictionary
  • Iterators
• Modules

Indices and tables

• Index
• Search Page