itc-tur

opusTCv20210807_transformer-big_2022-07-28.zip

• dataset: opusTCv20210807
• model: transformer-big
• source language(s): cat fra gcf_Latn glg ita lad lad_Latn lat_Latn mol oci osp_Latn pob por ron spa
• target language(s): tur
• raw source language(s): cat fra gcf glg ita lad lat mol oci osp pob por ron spa
• raw target language(s): tur
• model: transformer-big
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807_transformer-big_2022-07-28.zip
• test set translations: opusTCv20210807_transformer-big_2022-07-28.test.txt
• test set scores: opusTCv20210807_transformer-big_2022-07-28.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.cat-tur	22.3	0.57880	19	95	1.000
Tatoeba-test-v2021-08-07.fra-tur	34.0	0.62203	2582	14305	0.990
Tatoeba-test-v2021-08-07.gcf-tur	0.0	4.386	1	2	1.000
Tatoeba-test-v2021-08-07.glg-tur	100.0	10.00000	1	5	1.000
Tatoeba-test-v2021-08-07.ita-tur	35.3	0.60286	10000	75806	1.000
Tatoeba-test-v2021-08-07.lad_Latn-tur	34.0	0.57011	45	206	0.995
Tatoeba-test-v2021-08-07.lad-tur	16.8	0.42814	62	281	1.000
Tatoeba-test-v2021-08-07.lat-tur	9.0	0.21367	122	641	0.965
Tatoeba-test-v2021-08-07.multi-tur	38.2	0.64715	10000	61259	0.994
Tatoeba-test-v2021-08-07.oci-tur	9.5	0.38479	52	281	1.000
Tatoeba-test-v2021-08-07.osp-tur	35.4	0.53955	1	4	1.000
Tatoeba-test-v2021-08-07.por-tur	39.6	0.67253	1794	9311	0.944
Tatoeba-test-v2021-08-07.ron-tur	34.4	0.63326	2460	13785	0.976
Tatoeba-test-v2021-08-07.spa-tur	45.3	0.71552	10615	56098	0.949