|
--- |
|
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: [wmt24-en-is-transformer-base](https://huggingface.co/arnastofnun/wmt24-en-is-transformer-base), [wmt24-en-is-transformer-base-deep](https://huggingface.co/arnastofnun/wmt24-en-is-transformer-base-deep), [wmt24-en-is-transformer-big-deep](https://huggingface.co/arnastofnun/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 |
|
|
|
```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 = TRANSLATION_MODEL.translate(src_sentences) |
|
print(translated_sentences) |
|
``` |
|
|
|
## Eval results |
|
We evaluated our data on the [WMT21 test set](https://github.com/wmt-conference/wmt21-news-systems/). These are the chrF scores for our published models: |
|
|
|
| model | chrF | |
|
|:---------------|:------| |
|
| Base | 56.8 | |
|
| Base_deep | 57.1 | |
|
| Big | 57.7 | |
|
| Big_deep | 57.7 | |
|
## BibTeX entry and citation info |
|
|
|
```bibtex |
|
@inproceedings{jasonarson2024cogsinamachine, |
|
year={2024}, |
|
title={Cogs in a Machine, Doing What They’re Meant to Do \\– The AMI Submission to the WMT24 General Translation Task}, |
|
author={Atli Jasonarson, Hinrik Hafsteinsson, Bjarki Ármannsson, Steinþór Steingrímsson}, |
|
organization={The Árni Magnússon Institute for Icelandic Studies} |
|
} |
|
``` |
|
|