Contents

Getting Started

• Overview
  • Installation
  • Citation
  • Additional resources
• Краткое руководство
  • Step 1: Preprocess the data
  • Step 2: Train the model
  • Step 3: Translate
• Вопросы и ответы
  • How do I use Pretrained embeddings (e.g. GloVe)?
  • How do I use the Transformer model? Do you support multi-gpu?
  • How can I ensemble Models at inference?
• Contributors
  • Guidelines
• References

Examples

• Library
• Translation
• Summarization
  • Preprocessing the data
  • Training
  • Inference
  • Evaluation
  • Scores and Models
  • References
• Image to Text
  • Dependencies
  • Quick Start
  • Options
• Speech to Text
  • Dependencies
  • Quick Start
  • Options
  • Acknowledgement

Scripts

• Preprocess
  • Named Arguments
  • Data
  • Vocab
  • Pruning
  • Random
  • Logging
  • Speech
• Train
  • Named Arguments
  • Model-Embeddings
  • Model-Embedding Features
  • Model- Encoder-Decoder
  • Model- Attention
  • General
  • Initialization
  • Optimization- Type
  • Optimization- Rate
  • Logging
  • Speech
• Translate
  • Named Arguments
  • Model
  • Data
  • Random Sampling
  • Beam
  • Logging
  • Efficiency
  • Speech
• Server
  • Named Arguments

API

• Framework
  • Model
  • Trainer
  • Loss
  • Optimizer
• Modules
  • Core Modules
  • Encoders
  • Decoders
  • Attention
  • Architecture: Transfomer
  • Architecture: Conv2Conv
  • Architecture: SRU
  • Alternative Encoders
  • Copy Attention
  • Structured Attention
• Translation
  • Translations
  • Translator Class
  • Decoding Strategies
  • Scoring
• Server
  • Models
  • Core Server
• Data Loaders
  • Data Readers
  • Dataset