wszlong / transformer Public

Notifications You must be signed in to change notification settings
Fork 6
Star 25

A simple TensorFlow implementation of the Transformer

25 stars 6 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 68 Commits
models		models
utils		utils
README.md		README.md
__init__.py		__init__.py
datagen.sh		datagen.sh
run.py		run.py
test.sh		test.sh
train.sh		train.sh

Repository files navigation

A simple Tensorflow implementation of the Transformer

This project is a simple implementation of Tensor2tensor (https://github.com/tensorflow/tensor2tensor) for machine translation.

How to use?

Preprosessing. Prepare the parallel data (token, bpe, vocab, and so on), run ./datagen.sh to generate data.
Training. Modify the model params (transformer_params_big or transformer_params_base, basic params are set in models/common_hparms.py), and run ./train.sh.
inference. Run the command to translate source sentence: ./test.sh.

C++ Version Translator

Once we have trained the model, we can also use a C++/CUDA Transformer-translator to translate source language.

Contact

If you have questions, suggestions and bug reports, please email [email protected].

About

A simple TensorFlow implementation of the Transformer

translation transformer attention-is-all-you-need

Report repository

Releases

No releases published

Packages

No packages published

Languages