gmq-eng

opus-2020-06-28.zip

• dataset: opus
• model: transformer
• source language(s): dan fao isl non_Latn swe
• 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.dan-eng.dan.eng	59.5	0.738
Tatoeba-test.fao-eng.fao.eng	23.1	0.445
Tatoeba-test.isl-eng.isl.eng	49.5	0.656
Tatoeba-test.multi.eng	57.4	0.718
Tatoeba-test.non-eng.non.eng	33.7	0.499
Tatoeba-test.swe-eng.swe.eng	61.0	0.737

opus-2020-07-04.zip

• dataset: opus
• model: transformer
• source language(s): dan fao isl non_Latn swe
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2020-07-04.zip
• test set translations: opus-2020-07-04.test.txt
• test set scores: opus-2020-07-04.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.dan-eng.dan.eng	59.9	0.741
Tatoeba-test.fao-eng.fao.eng	22.0	0.419
Tatoeba-test.isl-eng.isl.eng	49.9	0.658
Tatoeba-test.multi.eng	58.9	0.728
Tatoeba-test.non-eng.non.eng	29.8	0.462
Tatoeba-test.swe-eng.swe.eng	61.0	0.739

opus-2020-07-19.zip

• dataset: opus
• model: transformer
• source language(s): dan fao isl nno nob nob_Hebr non_Latn swe
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2020-07-19.zip
• test set translations: opus-2020-07-19.test.txt
• test set scores: opus-2020-07-19.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.dan-eng.dan.eng	59.4	0.738
Tatoeba-test.fao-eng.fao.eng	23.3	0.443
Tatoeba-test.isl-eng.isl.eng	49.5	0.654
Tatoeba-test.multi.eng	57.4	0.715
Tatoeba-test.non-eng.non.eng	36.2	0.539
Tatoeba-test.nor-eng.nor.eng	53.2	0.686
Tatoeba-test.swe-eng.swe.eng	60.8	0.737

opus2m-2020-08-12.zip

• dataset: opus2m
• model: transformer
• source language(s): dan fao isl nno nob nob_Hebr non_Latn swe
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• 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.dan-eng.dan.eng	60.2	0.743
Tatoeba-test.fao-eng.fao.eng	24.4	0.447
Tatoeba-test.isl-eng.isl.eng	50.7	0.666
Tatoeba-test.multi.eng	58.1	0.720
Tatoeba-test.non-eng.non.eng	27.2	0.506
Tatoeba-test.nor-eng.nor.eng	53.7	0.689
Tatoeba-test.swe-eng.swe.eng	61.5	0.741

opus1m+bt-2021-05-01.zip

• dataset: opus1m+bt
• model: transformer-align
• source language(s): dan fao isl nno nob non swe
• target language(s): eng
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus1m+bt-2021-05-01.zip
• test set translations: opus1m+bt-2021-05-01.test.txt
• test set scores: opus1m+bt-2021-05-01.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.dan-eng	60.4	0.745	10000	73603	0.979
Tatoeba-test.fao-eng	25.3	0.444	294	1984	1.000
Tatoeba-test.isl-eng	49.8	0.659	2500	19763	0.972
Tatoeba-test.multi-eng	58.5	0.724	10000	72998	0.976
Tatoeba-test.nno-eng	49.3	0.643	460	3523	0.964
Tatoeba-test.nob-eng	55.7	0.707	4539	36821	0.971
Tatoeba-test.non-eng	27.8	0.492	15	145	1.000
Tatoeba-test.nor-eng	55.1	0.701	5000	40352	0.971
Tatoeba-test.swe-eng	61.4	0.741	10000	65998	0.980

opus4m+btTCv20210807-2021-09-30.zip

• dataset: opus4m+btTCv20210807
• model: transformer
• source language(s): dan fao isl nno nob non swe
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus4m+btTCv20210807-2021-09-30.zip
• test set translations: opus4m+btTCv20210807-2021-09-30.test.txt
• test set scores: opus4m+btTCv20210807-2021-09-30.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.multi-eng	58.6	0.722	10000	72131	0.988
Tatoeba-test-v2021-08-07.multi-multi	58.6	0.722	10000	72131	0.988

opus4m+btTCv20210807-2021-12-08.zip

• dataset: opus4m+btTCv20210807
• model: transformer-big
• source language(s): dan fao isl nno nob nob_Zinh non_Latn swe
• target language(s): eng
• raw source language(s): dan fao isl nno nob non swe
• raw target language(s): eng
• model: transformer-big
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus4m+btTCv20210807-2021-12-08.zip
• test set translations: opus4m+btTCv20210807-2021-12-08.test.txt
• test set scores: opus4m+btTCv20210807-2021-12-08.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.dan-eng	56.7	0.7159	10795	79668	0.991
Tatoeba-test-v2021-08-07.fao-eng	15.3	0.3680	294	1984	1.000
Tatoeba-test-v2021-08-07.isl-eng	42.0	0.5915	2503	19788	0.989
Tatoeba-test-v2021-08-07.multi-eng	54.5	0.6912	10000	72131	0.991
Tatoeba-test-v2021-08-07.non-eng	34.1	0.4989	15	145	1.000
Tatoeba-test-v2021-08-07.swe-eng	57.0	0.7027	10362	68509	0.995

opusTCv20210807+bt_transformer-big_2022-03-09.zip

• dataset: opusTCv20210807+bt
• model: transformer-big
• source language(s): dan fao isl nno nob non swe
• target language(s): eng
• raw source language(s): dan fao isl nno nob non swe
• raw target language(s): eng
• model: transformer-big
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807+bt_transformer-big_2022-03-09.zip
• test set translations: opusTCv20210807+bt_transformer-big_2022-03-09.test.txt
• test set scores: opusTCv20210807+bt_transformer-big_2022-03-09.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.dan-eng	65.4	0.78016	10795	79668	0.987
Tatoeba-test-v2021-08-07.fao-eng	31.3	0.48235	294	1984	1.000
Tatoeba-test-v2021-08-07.isl-eng	52.6	0.67868	2503	19788	0.980
Tatoeba-test-v2021-08-07.multi-eng	63.7	0.76120	10000	73075	0.986
Tatoeba-test-v2021-08-07.nno-eng	55.3	0.69248	460	3523	0.977
Tatoeba-test-v2021-08-07.nob-eng	60.0	0.73341	4539	36821	0.976
Tatoeba-test-v2021-08-07.non-eng	45.7	0.57677	15	145	1.000
Tatoeba-test-v2021-08-07.nor-eng	59.5	0.72976	5000	40352	0.977
Tatoeba-test-v2021-08-07.swe-eng	65.8	0.77243	10362	68509	0.989