FSMT
Model description
This is a ported version of fairseq wmt19 transformer for en-de.
For more details, please see, Facebook FAIR's WMT19 News Translation Task Submission.
The abbreviation FSMT stands for FairSeqMachineTranslation
All four models are available:
Intended uses & limitations
How to use
from transformers import FSMTForConditionalGeneration, FSMTTokenizer
mname = "facebook/wmt19-en-de"
tokenizer = FSMTTokenizer.from_pretrained(mname)
model = FSMTForConditionalGeneration.from_pretrained(mname)
input = "Machine learning is great, isn't it?"
input_ids = tokenizer.encode(input, return_tensors="pt")
outputs = model.generate(input_ids)
decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded) # Maschinelles Lernen ist großartig, oder?
Limitations and bias
- The original (and this ported model) doesn't seem to handle well inputs with repeated sub-phrases, content gets truncated
Training data
Pretrained weights were left identical to the original model released by fairseq. For more details, please, see the paper.
Eval results
pair | fairseq | transformers |
---|---|---|
en-de | 43.1 | 42.83 |
The score is slightly below the score reported by fairseq
, since `transformers`` currently doesn't support:
- model ensemble, therefore the best performing checkpoint was ported (
model4.pt
). - re-ranking
The score was calculated using this code:
git clone https://github.com/huggingface/transformers
cd transformers
export PAIR=en-de
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
note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with --num_beams 50
.
Data Sources
BibTeX entry and citation info
@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},
}
TODO
- port model ensemble (fairseq uses 4 model checkpoints)
- Downloads last month
- 22,501
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.