hun-eng

opus-2021-02-19.zip

• dataset: opus
• model: transformer
• source language(s): hun
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2021-02-19.zip
• test set translations: opus-2021-02-19.test.txt
• test set scores: opus-2021-02-19.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
newssyscomb2009.hun-eng	23.5	0.516	502	11821	0.965
newstest2009.hun-eng	22.5	0.510	2525	65402	0.963
Tatoeba-test.hun-eng	51.4	0.675	10000	69326	0.981

opus+bt-2021-04-30.zip

• dataset: opus+bt
• model: transformer-align
• source language(s): hun
• 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
newssyscomb2009.hun-eng	23.4	0.519	502	11821	0.973
newstest2009.hun-eng	22.4	0.513	2525	65402	0.967
Tatoeba-test.hun-eng	51.4	0.677	10000	69326	0.980

opusTCv20210807+bt_transformer-big_2022-03-09.zip

• dataset: opusTCv20210807+bt
• model: transformer-big
• source language(s): hun
• target language(s): eng
• raw source language(s): hun
• 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
newssyscomb2009.hun-eng	24.7	0.52550	502	11821	0.960
newstest2009.hun-eng	23.4	0.51701	2525	65402	0.960
Tatoeba-test-v2021-08-07.hun-eng	50.8	0.67001	10000	72821	0.962