---
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](https://arxiv.org/pdf/1706.03762) and was trained with [fairseq](https://github.com/facebookresearch/fairseq) for [WMT24](https://www2.statmt.org/wmt24/).

This is the base version of our model. See also: [base_deep](hlekkur), [big](hlekkur), [big_deep](hlekkur).

| 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

```python
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

```bibtex
@inproceedings{...,
year={XXX},
title={XXX},
author={XXX},
booktitle={XXX},
}
```