This is a Bert version of Pytorch port of OpenNMT, an open-source (MIT) neural machine translation system. It is designed to be research friendly to try out new ideas in translation, summary, image-to-text, morphology, and many other domains. Some companies have proven the code to be production ready.

We love contributions. Please consult the Issues page for any Contributions Welcome tagged post.

Before raising an issue, make sure you read the requirements and the documentation examples.

Unless there is a bug, please use the Forum or Gitter to ask questions.

• Full Documentation
• Requirements
• Features
• Quickstart
• Run on FloydHub
• Acknowledgements
• Citation

All dependencies can be installed via:

pip install -r requirements.txt

Note that we currently only support PyTorch 1.0.0

• data preprocessing
• Inference (translation) with batching and beam search
• Multiple source and target RNN (lstm/gru) types and attention (dotprod/mlp) types
• TensorBoard
• Source word features
• Pretrained Embeddings
• Copy and Coverage Attention
• Image-to-text processing
• Speech-to-text processing
• "Attention is all you need"
• Multi-GPU
• Inference time loss functions.
• [Conv2Conv convolution model]
• SRU "RNNs faster than CNN" paper
• FP16 training (mixed-precision with Apex)

Full Documentation

python preprocess.py -train_src data/src-train.txt -train_tgt data/tgt-train.txt -valid_src data/src-val.txt -valid_tgt data/tgt-val.txt -save_data data/demo

We will be working with some example data in data/ folder.

The data consists of parallel source (src) and target (tgt) data containing one sentence per line with tokens separated by a space:

• src-train.txt
• tgt-train.txt
• src-val.txt
• tgt-val.txt

Validation files are required and used to evaluate the convergence of the training. It usually contains no more than 5000 sentences.

After running the preprocessing, the following files are generated:

• demo.train.pt: serialized PyTorch file containing training data
• demo.valid.pt: serialized PyTorch file containing validation data
• demo.vocab.pt: serialized PyTorch file containing vocabulary data

Internally the system never touches the words themselves, but uses these indices.

python train.py -data data/demo -save_model demo-model

The main train command is quite simple. Minimally it takes a data file and a save file. This will run the default model, which consists of a 2-layer LSTM with 500 hidden units on both the encoder/decoder. If you want to train on GPU, you need to set, as an example: CUDA_VISIBLE_DEVICES=1,3 -world_size 2 -gpu_ranks 0 1 to use (say) GPU 1 and 3 on this node only. To know more about distributed training on single or multi nodes, read the FAQ section.

python translate.py -model demo-model_acc_XX.XX_ppl_XXX.XX_eX.pt -src data/src-test.txt -output pred.txt -replace_unk -verbose

Now you have a model which you can use to predict on new data. We do this by running beam search. This will output predictions into pred.txt.

!!! note "Note" The predictions are going to be quite terrible, as the demo dataset is small. Try running on some larger datasets! For example you can download millions of parallel sentences for translation or summarization.

Click this button to open a Workspace on FloydHub for training/testing your code.

Go to tutorial: How to use GloVe pre-trained embeddings in OpenNMT-py

The following pretrained models can be downloaded and used with translate.py.

http://opennmt.net/Models-py/

This is a BERT-based version of OpenNMT-py and the implementation is based on the OpenNMT-py

Authors:
Shakeel Ahmad Sheikh