ukr-hun

opus-2021-02-18.zip

• dataset: opus
• model: transformer-align
• source language(s): ukr
• target language(s): hun
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2021-02-18.zip
• test set translations: opus-2021-02-18.test.txt
• test set scores: opus-2021-02-18.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.ukr-hun	41.4	0.649	464	2433	0.974

opusTCv20210807+pft_transformer-align_2022-03-08.zip

• dataset: opusTCv20210807+pft
• model: transformer-align
• source language(s): ukr
• target language(s): hun
• raw source language(s): ukr
• raw target language(s): hun
• model: transformer-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807+pft_transformer-align_2022-03-08.zip
• test set translations: opusTCv20210807+pft_transformer-align_2022-03-08.test.txt
• test set scores: opusTCv20210807+pft_transformer-align_2022-03-08.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.ukr-hun	44.0	0.67544	473	2472	0.978

opusTCv20210807+pft-sepvoc_transformer-tiny11-align_2022-03-13.zip

• dataset: opusTCv20210807+pft
• model: transformer-tiny11-align
• source language(s): ukr
• target language(s): hun
• raw source language(s): ukr
• raw target language(s): hun
• model: transformer-tiny11-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807+pft-sepvoc_transformer-tiny11-align_2022-03-13.zip
• test set translations: opusTCv20210807+pft-sepvoc_transformer-tiny11-align_2022-03-13.test.txt
• test set scores: opusTCv20210807+pft-sepvoc_transformer-tiny11-align_2022-03-13.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.ukr-hun	42.2	0.65065	473	2472	0.979

opusTCv20210807+bt+pbt+pft-sepvoc_transformer-tiny11-align_2022-03-16.zip

• dataset: opusTCv20210807+bt+pbt+pft
• model: transformer-tiny11-align
• source language(s): ukr
• target language(s): hun
• raw source language(s): ukr
• raw target language(s): hun
• model: transformer-tiny11-align
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opusTCv20210807+bt+pbt+pft-sepvoc_transformer-tiny11-align_2022-03-16.zip
• test set translations: opusTCv20210807+bt+pbt+pft-sepvoc_transformer-tiny11-align_2022-03-16.test.txt
• test set scores: opusTCv20210807+bt+pbt+pft-sepvoc_transformer-tiny11-align_2022-03-16.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test-v2021-08-07.ukr-hun	42.5	0.66840	473	2472	0.982