This is the Seq2Seq model for the Machine Translation task, using Pytorch
Use LSTM as encoder to map input sentence to vector and another LSTM to decode target sentence from the vector. This Example use bentrevett/multi30k
from datasets
To train the Seq2Seq model, use the command line:
python main.py --config config.yaml
To test the Seq2Seq model, go to main.py and command these codes:
logging.info("Training started...")
Train_Task(config).train()
logging.info("Train complete")