|
--- |
|
language: |
|
- en |
|
- de |
|
- multilingual |
|
license: cc-by-sa-4.0 |
|
tags: |
|
- translation |
|
- wmt20 |
|
datasets: |
|
- wmt/europarl |
|
- para_crawl |
|
- german-nlp-group/german_common_crawl |
|
- wmt/news-commentary |
|
- wmt/wikititles |
|
--- |
|
|
|
# Fairseq En-De NMT WMT20 MLQE |
|
|
|
This repository contains the English-German model trained with the [fairseq toolkit](https://github.com/pytorch/fairseq) that was used to produce translations used in the WMT20 shared task on quality estimation (QE) on the [MLQE dataset](https://github.com/facebookresearch/mlqe). |
|
|
|
The checkpoint was converted from the original fairseq checkpoint available [here](https://github.com/facebookresearch/mlqe/tree/master/nmt_models) using the `convert_fsmt_original_pytorch_checkpoint_to_pytorch.py` script from the 🤗 Transformers library (v4.26.0). |
|
|
|
Please refer to the repositories linked above for additional information on usage, parameters and training data. |
|
|
