eng-tgl

opus-2020-06-17.zip

• dataset: opus
• model: transformer-align
• source language(s): eng
• target language(s): tgl_Latn
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2020-06-17.zip
• test set translations: opus-2020-06-17.test.txt
• test set scores: opus-2020-06-17.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.eng.tgl	26.5	0.571

opus-2021-02-23.zip

• dataset: opus
• model: transformer
• source language(s): eng
• target language(s): tgl
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• a sentence initial language token is required in the form of >>id<< (id = valid target language ID)
• valid language labels: >>tgl_Latn<< >>tgl<<
• download: opus-2021-02-23.zip
• test set translations: opus-2021-02-23.test.txt
• test set scores: opus-2021-02-23.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.eng-tgl	26.3	0.571	5000	35602	1.000
tico19-test.eng-tgl	31.9	0.603	2100	69112	0.975

opus+bt-2021-04-10.zip

• dataset: opus+bt
• model: transformer-align
• source language(s): eng
• target language(s): tgl
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• a sentence initial language token is required in the form of >>id<< (id = valid target language ID)
• valid language labels: >>tgl_Latn<< >>tgl<<
• download: opus+bt-2021-04-10.zip
• test set translations: opus+bt-2021-04-10.test.txt
• test set scores: opus+bt-2021-04-10.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.eng-tgl	26.3	0.570	5000	35602	1.000
tico19-test.eng-tgl	33.0	0.611	2100	69112	0.975