opus-mt-he-de
source languages: he
target languages: de
OPUS readme: he-de
dataset: opus
model: transformer-align
pre-processing: normalization + SentencePiece
download original weights: opus-2020-01-26.zip
test set translations: opus-2020-01-26.test.txt
test set scores: opus-2020-01-26.eval.txt
Benchmarks
testset | BLEU | chr-F |
---|---|---|
Tatoeba.he.de | 45.5 | 0.647 |
- Downloads last month
- 73
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.