deu-fin

opus-2021-01-03.zip

• dataset: opus
• model: transformer
• source language(s): deu
• target language(s): fin
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2021-01-03.zip
• test set translations: opus-2021-01-03.test.txt
• test set scores: opus-2021-01-03.eval.txt

Benchmarks

testset	BLEU	chr-F
goethe-institute-test1-deufin.deu.fin	18.6	0.501
goethe-institute-test2-deufin.deu.fin	18.3	0.498
Tatoeba-test.deu.fin	40.1	0.634
Tatoeba-test.deu-fin.deu.fin	40.1	0.634

opus-2021-02-16.zip

• dataset: opus
• model: transformer-align
• source language(s): deu
• target language(s): fin
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2021-02-16.zip
• test set translations: opus-2021-02-16.test.txt
• test set scores: opus-2021-02-16.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.deu-fin	40.3	0.634	2500	14145	0.944

opus-2021-02-17.zip

• dataset: opus
• model: transformer-align
• source language(s): deu
• target language(s): fin
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2021-02-17.zip
• test set translations: opus-2021-02-17.test.txt
• test set scores: opus-2021-02-17.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
goethe-institute-test1.deu-fin	18.5	0.499	2000	27070	0.935
goethe-institute-test2.deu-fin	18.0	0.496	2000	27014	0.929
Tatoeba-test.deu-fin	40.4	0.636	2500	14145	0.947

opus-2021-02-18.zip

• dataset: opus
• model: transformer-align
• source language(s): deu
• target language(s): fin
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2021-02-18.zip
• test set translations: opus-2021-02-18.test.txt
• test set scores: opus-2021-02-18.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
goethe-institute-test1.deu-fin	18.7	0.501	2000	27070	0.933
goethe-institute-test2.deu-fin	18.0	0.497	2000	27014	0.926
Tatoeba-test.deu-fin	40.2	0.635	2500	14145	0.948

opus+bt-2021-03-08.zip

• dataset: opus+bt
• model: transformer-align
• source language(s): deu
• target language(s): fin
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus+bt-2021-03-08.zip
• test set translations: opus+bt-2021-03-08.test.txt
• test set scores: opus+bt-2021-03-08.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
goethe-institute-test1.deu-fin	20.7	0.528	2000	27070	0.946
goethe-institute-test2.deu-fin	20.0	0.523	2000	27014	0.939
Tatoeba-test.deu-fin	41.1	0.645	2500	14145	0.951

opusTCv20210807+bt-2021-09-10.zip

• dataset: opusTCv20210807+bt
• model: transformer-align
• source language(s): deu
• target language(s): fin
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807+bt-2021-09-10.zip
• test set translations: opusTCv20210807+bt-2021-09-10.test.txt
• test set scores: opusTCv20210807+bt-2021-09-10.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
goethe-institute-test1.deu-fin	21.6	0.536	2000	27070	0.952
goethe-institute-test2.deu-fin	21.4	0.535	2000	27014	0.948
Tatoeba-test-v2021-08-07.deu-fin	41.9	0.652	2647	15024	0.957