模型:
facebook/wmt19-ru-en
这是一个针对ru-en的端口版本 fairseq wmt19 transformer 的转换模型。
详情请参见 Facebook FAIR's WMT19 News Translation Task Submission 。
FSMT的缩写代表FairSeqMachineTranslation
所有四个模型可用:
from transformers import FSMTForConditionalGeneration, FSMTTokenizer mname = "facebook/wmt19-ru-en" tokenizer = FSMTTokenizer.from_pretrained(mname) model = FSMTForConditionalGeneration.from_pretrained(mname) input = "Машинное обучение - это здорово, не так ли?" 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?的限制和偏见
预训练的权重与fairseq发布的原始模型保持相同。更多详情请参见 paper 。
pair | fairseq | transformers |
---|---|---|
ru-en | 12311321 | 39.20 |
评分略低于fairseq报告的评分,因为“transformers”当前不支持:
使用以下代码计算了分数:
git clone https://github.com/huggingface/transformers cd transformers export PAIR=ru-en export DATA_DIR=data/$PAIR export SAVE_DIR=data/$PAIR export BS=8 export NUM_BEAMS=15 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 $PAIR PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py facebook/wmt19-$PAIR $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
注意:fairseq报告使用的是beam为50,因此如果使用--num_beams 50重新运行,应该能获得稍高的分数。
@inproceedings{..., year={2020}, title={Facebook FAIR's WMT19 News Translation Task Submission}, author={Ng, Nathan and Yee, Kyra and Baevski, Alexei and Ott, Myle and Auli, Michael and Edunov, Sergey}, booktitle={Proc. of WMT}, }