Modelpublic

DigitalUmuganda/joeynmt-en-kin

sourceHugging Faceupdated 4y agoView on Hugging Face

0likes

Model Card

English-to-Kinyarwanda Machine Translation

This model is an English-to-Kinyarwanda machine translation model, it was built and trained using JoeyNMT framework. The translation model uses transformer encoder-decoder based architecture. It was trained on a 47,211 long English-Kinyarwanda bitext dataset prepared by Digital Umuganda.

Model architecture

Encoder && Decoder

Type: Transformer

Numlayer: 6 Numheads: 8 Embeddingdim: 256 ffsize: 1024 Dropout: 0.1 Layer_norm: post Initializer: xavier Total params: 12563968

Pre-processing

Tokenizertype: subword-nmt nummerges: 4000 BPE encoding learned on the bitext, separate vocabularies for each language Pretokenizer: None No lowercase applied

Training

Optimizer: Adam Loss: crossentropy Epochs: 30 Batch_size: 256 Number of GPUs: 1

Evaluation

Evaluationmetrics: Bluescore, chrf Tokenization: None Beamwidth: 15 Beamalpha: 1.0

Tools

—joeyNMT 2.0.0
—datasets
—pandas
—numpy
—transformers
—sentencepiece
—pytorch(with cuda)
—sacrebleu
—protobuf>=3.20.1

How to train

Use the following link for more information

Translation

To install joeyNMT run:

$ git clone https://github.com/joeynmt/joeynmt.git

$ cd joeynmt $ pip install . -e

Interactive translation(stdin):

$ python -m joeynmt translate args.yaml

File translation:

$ python -m joeynmt translate args.yaml < srclang.txt > hypothesistrg_lang.txt

Accuracy measurement

Sacrebleu installation:

$ pip install sacrebleu

Measurement(bleu_score, chrf):

$ sacrebleu reference.tsv -i hypothesis.tsv -m bleu chrf

To-do

Test the model using differenct datasets including the jw300 Use the Digital Umuganda dataset on some of the available State Of The Art(SOTA) available models. * Expand the dataset

Result

The following result were obtained on using the sacrebleu.

English-to-Kinyarwanda:

Blue: 56.5

Chrf: 75.2