Contents

• Overview
  • التركيب
  • Citation
  • Additional resources
• بداية سريعة
  • الخطوة 1: Preprocess the data
  • الخطوة 2: تدريب النموذج 
  • الخطوة 3: الترجمة
• Doc: Framework
  • Model
  • Trainer
  • Loss
  • Optim
• Doc: Modules
  • Core Modules
  • Encoders
  • Decoders
  • Attention
  • Architecture: Transfomer
  • Architecture: Conv2Conv
  • Architecture: SRU
  • Alternative Encoders
  • Copy Attention
  • Structured Attention
• Doc: Translation
  • Translations
  • Translator Class
  • Beam Search
• Doc: Data Loaders
  • Datasets
• Library: Example
• Options: preprocess.py:
  • Data:
  • Vocab:
  • Pruning:
  • Random:
  • Logging:
  • Speech:
• Options: train.py:
  • Model-Embeddings:
  • Model-Embedding Features:
  • Model- Encoder-Decoder:
  • Model- Attention:
  • General:
  • Initialization:
  • Optimization- Type:
  • Optimization- Rate:
  • Logging:
  • Speech:
• Options: translate.py:
  • Model:
  • Data:
  • Beam:
  • Logging:
  • Efficiency:
  • Speech:
• Example: Translation
• Example: Summarization
  • Preprocessing the data
  • Training
  • Inference
  • Evaluation
  • Scores and Models
  • References
• Example: Image to Text
  • Dependencies
  • Quick Start
  • Options
• Example: Speech to Text
  • Dependencies
  • Quick Start
  • Options
  • Acknowledgement
• اسئلة متكررة 
  • 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
• References