ContentsΒΆ
Getting Started
Frequently Asked Questions
MAMMOTH features
Tutorials
Scripts
- Train
- Configuration
- Data/Tasks
- Vocab
- Transform/Denoising AE
- Transform/InferFeats
- Transform/SwitchOut
- Transform/Token_Drop
- Transform/Token_Mask
- Transform/Length filter
- Transform/Word ratio filter
- Transform/Repetitions filter
- Transform/Terminal punctuation filter
- Transform/Non-zero numerals filter
- Transform/Subword/Common
- Model- Embeddings
- Model- Encoder-Decoder
- Model- Attention
- Generator
- Attention bridge
- General
- Computation Environment
- Reproducibility
- Initialization
- Fine-grained Parameter Freezing
- Batching
- Logging
- Beam Search
- Random Sampling
- Penalties
- Decoding tricks
- Translate
- Configuration
- Data/Tasks
- Vocab
- Transform/Denoising AE
- Transform/InferFeats
- Transform/SwitchOut
- Transform/Token_Drop
- Transform/Token_Mask
- Transform/Length filter
- Transform/Word ratio filter
- Transform/Repetitions filter
- Transform/Terminal punctuation filter
- Transform/Non-zero numerals filter
- Transform/Subword/Common
- Model
- Data
- Beam Search
- Random Sampling
- Reproducibility
- Penalties
- Decoding tricks
- Logging
- Efficiency
- Server