itc-heb

opus1m-2021-05-16.zip

• dataset: opus1m
• model: transformer-align
• source language(s): cat fra gcf
• target language(s): heb
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus1m-2021-05-16.zip
• test set translations: opus1m-2021-05-16.test.txt
• test set scores: opus1m-2021-05-16.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.cat-heb	100.0	1.000	1	7	1.000
Tatoeba-test.fra-heb	33.2	0.547	3281	20645	1.000
Tatoeba-test.gcf-heb	0.0	1.000	1	2	1.000
Tatoeba-test.ita-heb	2.6	0.157	1706	9790	1.000
Tatoeba-test.lad-heb	1.0	0.149	137	715	1.000
Tatoeba-test.lat-heb	0.8	0.119	224	1307	1.000
Tatoeba-test.multi-heb	33.6	0.552	3283	20664	1.000
Tatoeba-test.osp-heb	9.5	0.219	2	7	1.000
Tatoeba-test.por-heb	1.8	0.171	702	4336	1.000
Tatoeba-test.ron-heb	16.0	0.122	1	3	1.000
Tatoeba-test.spa-heb	6.4	0.241	1849	12105	1.000

opusTCv20210807_transformer-big_2022-08-03.zip

• dataset: opusTCv20210807
• model: transformer-big
• source language(s): cat fra gcf_Latn glg ita lad lad_Latn lat_Latn mol osp_Latn pob por ron spa
• target language(s): heb
• raw source language(s): cat fra gcf glg ita lad lat mol osp pob por ron spa
• raw target language(s): heb
• model: transformer-big
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807_transformer-big_2022-08-03.zip
• test set translations: opusTCv20210807_transformer-big_2022-08-03.test.txt
• test set scores: opusTCv20210807_transformer-big_2022-08-03.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.cat-heb	87.2	0.94170	3	16	1.000
Tatoeba-test-v2021-08-07.fra-heb	39.2	0.60191	3281	20645	1.000
Tatoeba-test-v2021-08-07.gcf-heb	0.0	10.00000	1	2	1.000
Tatoeba-test-v2021-08-07.glg-heb	35.0	0.64581	1	6	0.819
Tatoeba-test-v2021-08-07.ita-heb	40.4	0.60230	1706	9790	0.989
Tatoeba-test-v2021-08-07.lad-heb	11.9	0.30460	218	1086	1.000
Tatoeba-test-v2021-08-07.lad_Latn-heb	21.4	0.44320	131	681	1.000
Tatoeba-test-v2021-08-07.lat-heb	4.5	0.16949	271	1525	1.000
Tatoeba-test-v2021-08-07.multi-heb	40.6	0.60662	7914	48809	1.000
Tatoeba-test-v2021-08-07.osp-heb	100.0	10.00000	3	10	1.000
Tatoeba-test-v2021-08-07.por-heb	43.2	0.62256	719	4418	1.000
Tatoeba-test-v2021-08-07.ron-heb	16.7	0.48715	6	34	1.000
Tatoeba-test-v2021-08-07.spa-heb	44.4	0.63914	1849	12105	0.987