opus-2020-06-28.zip

dataset: opus
model: transformer
source language(s): akl_Latn ceb hil ilo pag pmn war
target language(s): eng
model: transformer
pre-processing: normalization + SentencePiece (spm32k,spm32k)
download: opus-2020-06-28.zip
test set translations: opus-2020-06-28.test.txt
test set scores: opus-2020-06-28.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.akl-eng.akl.eng	7.3	0.295
Tatoeba-test.ceb-eng.ceb.eng	19.8	0.373
Tatoeba-test.hil-eng.hil.eng	20.7	0.395
Tatoeba-test.ilo-eng.ilo.eng	33.5	0.538
Tatoeba-test.multi.eng	16.4	0.320
Tatoeba-test.pag-eng.pag.eng	25.3	0.452
Tatoeba-test.pmn-eng.pmn.eng	0.7	0.110
Tatoeba-test.war-eng.war.eng	14.1	0.349

opus-2020-07-27.zip

dataset: opus
model: transformer
source language(s): akl_Latn ceb hil ilo pag war
target language(s): eng
model: transformer
pre-processing: normalization + SentencePiece (spm12k,spm12k)
download: opus-2020-07-27.zip
test set translations: opus-2020-07-27.test.txt
test set scores: opus-2020-07-27.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.akl-eng.akl.eng	5.6	0.208
Tatoeba-test.ceb-eng.ceb.eng	21.4	0.391
Tatoeba-test.hil-eng.hil.eng	9.3	0.280
Tatoeba-test.ilo-eng.ilo.eng	1.6	0.164
Tatoeba-test.multi.eng	21.0	0.385
Tatoeba-test.pag-eng.pag.eng	1.9	0.182
Tatoeba-test.pmn-eng.pmn.eng	0.6	0.102
Tatoeba-test.war-eng.war.eng	3.9	0.209

opus2m-2020-08-12.zip

dataset: opus2m
model: transformer
source language(s): akl_Latn ceb hil ilo pag war
target language(s): eng
model: transformer
pre-processing: normalization + SentencePiece (spm12k,spm12k)
download: opus2m-2020-08-12.zip
test set translations: opus2m-2020-08-12.test.txt
test set scores: opus2m-2020-08-12.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.akl-eng.akl.eng	11.6	0.321
Tatoeba-test.ceb-eng.ceb.eng	21.7	0.393
Tatoeba-test.hil-eng.hil.eng	17.6	0.371
Tatoeba-test.ilo-eng.ilo.eng	36.6	0.560
Tatoeba-test.multi.eng	21.5	0.391
Tatoeba-test.pag-eng.pag.eng	27.5	0.494
Tatoeba-test.war-eng.war.eng	17.3	0.380