fin-deu

opus-2021-01-03.zip

• dataset: opus
• model: transformer
• source language(s): fin
• target language(s): deu
• 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
Tatoeba-test.fin.deu	47.4	0.658
Tatoeba-test.fin-deu.fin.deu	47.4	0.658

opus-2021-02-18.zip

• dataset: opus
• model: transformer-align
• source language(s): fin
• target language(s): deu
• 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
Tatoeba-test.fin-deu	47.6	0.659	2500	18076	1.000

opusTCv20210807+bt-2021-09-12.zip

• dataset: opusTCv20210807+bt
• model: transformer-align
• source language(s): fin
• target language(s): deu
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807+bt-2021-09-12.zip
• test set translations: opusTCv20210807+bt-2021-09-12.test.txt
• test set scores: opusTCv20210807+bt-2021-09-12.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
goethe-institute-test1.fin-deu	25.4	0.550	2000	33995	1.000
goethe-institute-test2.fin-deu	26.5	0.559	1999	33836	1.000
Tatoeba-test-v2021-08-07.fin-deu	47.1	0.659	2647	19163	1.000