cel-eng

opus-2020-06-28.zip

• dataset: opus
• model: transformer
• source language(s): bre cor cym gla gle glv
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2020-06-28.zip
• test set translations: opus-2020-06-28.test.txt
• test set scores: opus-2020-06-28.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.bre-eng.bre.eng	15.2	0.362
Tatoeba-test.cor-eng.cor.eng	3.1	0.175
Tatoeba-test.cym-eng.cym.eng	38.3	0.564
Tatoeba-test.gla-eng.gla.eng	14.7	0.318
Tatoeba-test.gle-eng.gle.eng	50.0	0.660
Tatoeba-test.glv-eng.glv.eng	30.0	0.466
Tatoeba-test.multi.eng	22.1	0.391

opus-2020-07-26.zip

• dataset: opus
• model: transformer
• source language(s): bre cor cym gla gle glv
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2020-07-26.zip
• test set translations: opus-2020-07-26.test.txt
• test set scores: opus-2020-07-26.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.bre-eng.bre.eng	16.7	0.375
Tatoeba-test.cor-eng.cor.eng	2.7	0.175
Tatoeba-test.cym-eng.cym.eng	39.3	0.563
Tatoeba-test.gla-eng.gla.eng	13.7	0.312
Tatoeba-test.gle-eng.gle.eng	47.8	0.642
Tatoeba-test.glv-eng.glv.eng	45.2	0.614
Tatoeba-test.multi.eng	21.7	0.387

opus2m-2020-07-31.zip

• dataset: opus2m
• model: transformer
• source language(s): bre cor cym gla gle glv
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus2m-2020-07-31.zip
• test set translations: opus2m-2020-07-31.test.txt
• test set scores: opus2m-2020-07-31.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.bre-eng.bre.eng	17.2	0.385
Tatoeba-test.cor-eng.cor.eng	3.0	0.172
Tatoeba-test.cym-eng.cym.eng	41.5	0.582
Tatoeba-test.gla-eng.gla.eng	15.4	0.330
Tatoeba-test.gle-eng.gle.eng	50.8	0.668
Tatoeba-test.glv-eng.glv.eng	11.0	0.297
Tatoeba-test.multi.eng	22.8	0.398

opus4m-2020-08-12.zip

• dataset: opus4m
• model: transformer
• source language(s): bre cor cym gla gle glv
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus4m-2020-08-12.zip
• test set translations: opus4m-2020-08-12.test.txt
• test set scores: opus4m-2020-08-12.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.bre-eng.bre.eng	17.2	0.395
Tatoeba-test.cor-eng.cor.eng	3.2	0.177
Tatoeba-test.cym-eng.cym.eng	41.3	0.584
Tatoeba-test.gla-eng.gla.eng	16.3	0.337
Tatoeba-test.gle-eng.gle.eng	51.3	0.675
Tatoeba-test.glv-eng.glv.eng	17.0	0.525
Tatoeba-test.multi.eng	23.3	0.404

opus1m+bt-2021-05-01.zip

• dataset: opus1m+bt
• model: transformer-align
• source language(s): bre cor cym gla gle glv
• target language(s): eng
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus1m+bt-2021-05-01.zip
• test set translations: opus1m+bt-2021-05-01.test.txt
• test set scores: opus1m+bt-2021-05-01.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.bre-eng	30.0	0.471	383	2064	1.000
Tatoeba-test.cor-eng	3.5	0.184	3198	16828	1.000
Tatoeba-test.cym-eng	43.0	0.597	818	5563	1.000
Tatoeba-test.gla-eng	17.3	0.331	917	6365	1.000
Tatoeba-test.gle-eng	51.5	0.668	1924	11246	1.000
Tatoeba-test.glv-eng	6.2	0.250	5	27	1.000
Tatoeba-test.multi-eng	25.5	0.417	7245	42097	1.000

opus1m+bt-tuned4bre2eng-2021-05-08.zip

• dataset: opus1m+bt-tuned4bre2eng
• model: transformer-align
• source language(s): bre
• target language(s): eng
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus1m+bt-tuned4bre2eng-2021-05-08.zip
• test set translations: opus1m+bt-tuned4bre2eng-2021-05-08.test.txt
• test set scores: opus1m+bt-tuned4bre2eng-2021-05-08.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.bre-eng	32.3	0.502	383	2065	1.000
Tatoeba-test.multi-eng	6.6	0.188	7245	42097	1.000

opus4m+btTCv20210807-2021-09-30.zip

• dataset: opus4m+btTCv20210807
• model: transformer
• source language(s): bre cor cym gla gle glv
• target language(s): eng
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus4m+btTCv20210807-2021-09-30.zip
• test set translations: opus4m+btTCv20210807-2021-09-30.test.txt
• test set scores: opus4m+btTCv20210807-2021-09-30.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.bre-eng	30.2	0.469	383	2064	1.000
Tatoeba-test-v2021-08-07.cor-eng	6.2	0.217	3198	16828	1.000
Tatoeba-test-v2021-08-07.cym-eng	51.1	0.677	818	5563	1.000
Tatoeba-test-v2021-08-07.gla-eng	4.7	0.161	955	6610	1.000
Tatoeba-test-v2021-08-07.gle-eng	46.7	0.635	1913	11189	1.000
Tatoeba-test-v2021-08-07.glv-eng	20.8	0.419	5	27	1.000
Tatoeba-test-v2021-08-07.multi-eng	24.3	0.403	7272	42285	1.000
Tatoeba-test-v2021-08-07.multi-multi	24.3	0.403	7272	42285	1.000

opusTCv20210807+bt_transformer-big_2022-03-13.zip

• dataset: opusTCv20210807+bt
• model: transformer-big
• source language(s): bre cor cym gla gle glv
• target language(s): eng
• raw source language(s): bre cor cym gla gle glv
• raw target language(s): eng
• model: transformer-big
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807+bt_transformer-big_2022-03-13.zip
• test set translations: opusTCv20210807+bt_transformer-big_2022-03-13.test.txt
• test set scores: opusTCv20210807+bt_transformer-big_2022-03-13.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.bre-eng	33.2	0.50443	383	2064	1.000
Tatoeba-test-v2021-08-07.cor-eng	2.7	0.15316	3198	16828	1.000
Tatoeba-test-v2021-08-07.cym-eng	53.3	0.69235	818	5563	1.000
Tatoeba-test-v2021-08-07.gla-eng	10.7	0.24584	955	6610	1.000
Tatoeba-test-v2021-08-07.gle-eng	56.6	0.70850	1913	11189	1.000
Tatoeba-test-v2021-08-07.glv-eng	6.7	0.21638	5	27	1.000
Tatoeba-test-v2021-08-07.multi-eng	27.0	0.41882	7272	42285	1.000