Pipeline for training Stanford Seq2Seq Neural Machine Translation using PyTorch.
Pipeline for training Stanford Seq2Seq Neural Machine Translation using PyTorch. Model trained on IWSLT'15 English-Vietnamese. State-of-the-art on IWSLT'15 English-Vietnamese reference.
First, install dependencies:
# clone repo
git clone https://github.com/dayyass/neural_machine_translation.git
# install dependencies
cd neural_machine_translation
pip install -r requirements.txt
Parallel corpora for Machine Translation. More about it here.
Before train any models, you need to create vocabularies for two languages. More about it here.
Train Neural Machine Translation:
python train.py
At the beginning of the script there is a list of parameters (written in uppercase) for training that can be changed. Validation performed on every epoch, testing performed after the last epoch.
NotImplementedError: opened issue.
NotImplementedError: opened issue.
List of implemented models: