这是基于fairseq的wmt19 transformer德语-英语版本的移植模型。
有关更多详细信息，请参阅Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation。
目前提供两个模型：
from transformers import FSMTForConditionalGeneration, FSMTTokenizer
mname = "allenai/wmt19-de-en-6-6-base"
tokenizer = FSMTTokenizer.from_pretrained(mname)
model = FSMTForConditionalGeneration.from_pretrained(mname)
input = "Maschinelles Lernen ist großartig, nicht wahr?"
input_ids = tokenizer.encode(input, return_tensors="pt")
outputs = model.generate(input_ids)
decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded) # Machine learning is great, isn't it?
预训练权重与allenai发布的原始模型保持一致。更多详情，请参见论文。
以下是BLEU分数：
| model | transformers |
|---|---|
| wmt19-de-en-6-6-base | 38.37 |
该分数通过以下代码计算得出：
git clone https://github.com/huggingface/transformers
cd transformers
export PAIR=de-en
export DATA_DIR=data/$PAIR
export SAVE_DIR=data/$PAIR
export BS=8
export NUM_BEAMS=5
mkdir -p $DATA_DIR
sacrebleu -t wmt19 -l $PAIR --echo src > $DATA_DIR/val.source
sacrebleu -t wmt19 -l $PAIR --echo ref > $DATA_DIR/val.target
echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/wmt19-de-en-6-6-base $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS@misc{kasai2020deep,
title={Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation},
author={Jungo Kasai and Nikolaos Pappas and Hao Peng and James Cross and Noah A. Smith},
year={2020},
eprint={2006.10369},
archivePrefix={arXiv},
primaryClass={cs.CL}
}