metadata
license: apache-2.0
language:
- en
- is
library_name: fairseq
tags:
- translation
- wmt
Model description
This is a translation model which translates text from English to Icelandic. It follows the architecture of the transformer model described in Attention is All You Need and was trained with fairseq for WMT24.
This is the base version of our model. See also: wmt24-en-is-transformer-base-deep, wmt24-en-is-transformer-big, wmt24-en-is-transformer-big-deep.
| model | d_model | d_ff | h | N_enc | N_dec |
|---|---|---|---|---|---|
| Base | 512 | 2048 | 8 | 6 | 6 |
| Base_deep | 512 | 2048 | 8 | 36 | 12 |
| Big | 1024 | 4096 | 16 | 6 | 6 |
| Big_deep | 1024 | 4096 | 16 | 36 | 12 |
How to use
from fairseq.models.transformer import TransformerModel
TRANSLATION_MODEL_NAME = 'checkpoint_best.pt'
TRANSLATION_MODEL = TransformerModel.from_pretrained('path/to/model', checkpoint_file=TRANSLATION_MODEL_NAME, bpe='sentencepiece', sentencepiece_model='sentencepiece.bpe.model')
src_sentences = ['This is a test sentence.', 'This is another test sentence.']
translated_sentences = translate(translation_model=TRANSLATION_MODEL, sentences=src_sentences, beam=5)
print(translated_sentences)
Limitations and bias
Training data
Eval results
BibTeX entry and citation info
@inproceedings{...,
year={XXX},
title={XXX},
author={XXX},
booktitle={XXX},
}