pol-eng

opus-2021-02-18.zip

• dataset: opus
• model: transformer
• source language(s): pol
• target language(s): eng
• model: transformer
• 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.pol-eng	53.5	0.692	10000	75002	0.968

opus+bt-2021-04-30.zip

• dataset: opus+bt
• model: transformer-align
• source language(s): pol
• target language(s): eng
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus+bt-2021-04-30.zip
• test set translations: opus+bt-2021-04-30.test.txt
• test set scores: opus+bt-2021-04-30.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.pol-eng	53.6	0.692	10000	75002	0.965

opusTCv20210807+bt_transformer-big_2022-03-11.zip

• dataset: opusTCv20210807+bt
• model: transformer-big
• source language(s): pol
• target language(s): eng
• raw source language(s): pol
• raw target language(s): eng
• model: transformer-big
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807+bt_transformer-big_2022-03-11.zip
• test set translations: opusTCv20210807+bt_transformer-big_2022-03-11.test.txt
• test set scores: opusTCv20210807+bt_transformer-big_2022-03-11.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.pol-eng	56.0	0.71038	10000	75067	0.972