seq2seq

Attention-based sequence to sequence learning

Dependencies

How to use

Train a model (CONFIG is a YAML configuration file, such as config/default.yaml):

./seq2seq.sh CONFIG --train -v

Translate text using an existing model:

./seq2seq.sh CONFIG --decode FILE_TO_TRANSLATE --output OUTPUT_FILE

or for interactive decoding:

./seq2seq.sh CONFIG --decode

Example English→French model

This is the same model and dataset as Bahdanau et al. 2015.

config/WMT14/download.sh    # download WMT14 data into raw_data/WMT14
config/WMT14/prepare.sh     # preprocess the data, and copy the files to data/WMT14
./seq2seq.sh config/WMT14/baseline.yaml --train -v   # train a baseline model on this data

You should get similar BLEU scores as these (our model was trained on a single Titan X I for about 4 days).

Dev Test +beam Steps Time
25.04 28.64 29.22 240k 60h
25.25 28.67 29.28 330k 80h

Download this model here. To use this model, just extract the archive into the seq2seq/models folder, and run:

 ./seq2seq.sh models/WMT14/config.yaml --decode -v

Example German→English model

This is the same dataset as Ranzato et al. 2015.

config/IWSLT14/prepare.sh
./seq2seq.sh config/IWSLT14/baseline.yaml --train -v
Dev Test +beam Steps
28.32 25.33 26.74 44k

The model is available for download here.

Audio pre-processing

If you want to use the toolkit for Automatic Speech Recognition (ASR) or Automatic Speech Translation (AST), then you'll need to pre-process your audio files accordingly. This README details how it can be done. You'll need to install the Yaafe library, and use scripts/speech/extract-audio-features.py to extract MFCCs from a set of wav files.

Features

Credits