-
Notifications
You must be signed in to change notification settings - Fork 92
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
6 changed files
with
139 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,29 @@ | ||
| # opusTCv20210807_transformer-big_2022-06-23.zip | ||
|
|
||
| * dataset: opusTCv20210807 | ||
| * model: transformer-big | ||
| * source language(s): deu | ||
| * target language(s): ces csb csb_Latn dsb hsb pol | ||
| * raw source language(s): deu | ||
| * raw target language(s): ces csb dsb hsb pol | ||
| * model: transformer-big | ||
| * 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: | ||
| * download: [opusTCv20210807_transformer-big_2022-06-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-zlw/opusTCv20210807_transformer-big_2022-06-23.zip) | ||
| * test set translations: [opusTCv20210807_transformer-big_2022-06-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-zlw/opusTCv20210807_transformer-big_2022-06-23.test.txt) | ||
| * test set scores: [opusTCv20210807_transformer-big_2022-06-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu-zlw/opusTCv20210807_transformer-big_2022-06-23.eval.txt) | ||
|
|
||
| ## Benchmarks | ||
|
|
||
| | testset | BLEU | chr-F | #sent | #words | BP | | ||
| |---------|-------|-------|-------|--------|----| | ||
| | newssyscomb2009.deu-ces | 24.3 | 0.51989 | 502 | 10032 | 0.972 | | ||
| | news-test2008.deu-ces | 22.5 | 0.50867 | 2051 | 42484 | 0.971 | | ||
| | newstest2009.deu-ces | 22.7 | 0.50404 | 2525 | 55533 | 0.965 | | ||
| | newstest2010.deu-ces | 25.6 | 0.53479 | 2489 | 52958 | 1.000 | | ||
| | newstest2011.deu-ces | 22.5 | 0.50351 | 3003 | 65653 | 0.956 | | ||
| | newstest2012.deu-ces | 22.4 | 0.49827 | 3003 | 65456 | 0.956 | | ||
| | newstest2013.deu-ces | 25.6 | 0.52310 | 3000 | 57250 | 0.962 | | ||
| | newstest2019-decs.deu-ces | 23.3 | 0.50959 | 1997 | 43373 | 0.973 | | ||
| | Tatoeba-test-v2021-08-07.deu-multi | 40.0 | 0.61973 | 9824 | 62972 | 0.968 | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,20 @@ | ||
| # opusTCv20210807_transformer-big_2022-06-23.zip | ||
|
|
||
| * dataset: opusTCv20210807 | ||
| * model: transformer-big | ||
| * source language(s): fin | ||
| * target language(s): ita | ||
| * raw source language(s): fin | ||
| * raw target language(s): ita | ||
| * model: transformer-big | ||
| * pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| * download: [opusTCv20210807_transformer-big_2022-06-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-mode | ||
| ls/fin-ita/opusTCv20210807_transformer-big_2022-06-23.zip) | ||
| * test set translations: [opusTCv20210807_transformer-big_2022-06-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-ita/opusTCv20210807_transformer-big_2022-06-23.test.txt) | ||
| * test set scores: [opusTCv20210807_transformer-big_2022-06-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-ita/opusTCv20210807_transformer-big_2022-06-23.eval.txt) | ||
|
|
||
| ## Benchmarks | ||
|
|
||
| | testset | BLEU | chr-F | #sent | #words | BP | | ||
| |---------|-------|-------|-------|--------|----| | ||
| | Tatoeba-test-v2021-08-07.fin-ita | 46.4 | 0.67941 | 1039 | 6710 | 0.956 | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,19 @@ | ||
| # opusTCv20210807_transformer-big_2022-06-23.zip | ||
|
|
||
| * dataset: opusTCv20210807 | ||
| * model: transformer-big | ||
| * source language(s): fin | ||
| * target language(s): spa | ||
| * raw source language(s): fin | ||
| * raw target language(s): spa | ||
| * model: transformer-big | ||
| * pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| * download: [opusTCv20210807_transformer-big_2022-06-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-spa/opusTCv20210807_transformer-big_2022-06-23.zip) | ||
| * test set translations: [opusTCv20210807_transformer-big_2022-06-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-spa/opusTCv20210807_transformer-big_2022-06-23.test.txt) | ||
| * test set scores: [opusTCv20210807_transformer-big_2022-06-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-spa/opusTCv20210807_transformer-big_2022-06-23.eval.txt) | ||
|
|
||
| ## Benchmarks | ||
|
|
||
| | testset | BLEU | chr-F | #sent | #words | BP | | ||
| |---------|-------|-------|-------|--------|----| | ||
| | Tatoeba-test-v2021-08-07.fin-spa | 52.9 | 0.70029 | 2513 | 16912 | 0.973 | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,22 @@ | ||
| # opusTCv20210807_transformer-big_2022-06-23.zip | ||
|
|
||
| * dataset: opusTCv20210807 | ||
| * model: transformer-big | ||
| * source language(s): spa | ||
| * target language(s): fin | ||
| * raw source language(s): spa | ||
| * raw target language(s): fin | ||
| * model: transformer-big | ||
| * pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| * download: [opusTCv20210807_transformer-big_2022-06-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-mode | ||
| ls/spa-fin/opusTCv20210807_transformer-big_2022-06-23.zip) | ||
| * test set translations: [opusTCv20210807_transformer-big_2022-06-23.test.txt](https://object.pouta.csc. | ||
| fi/Tatoeba-MT-models/spa-fin/opusTCv20210807_transformer-big_2022-06-23.test.txt) | ||
| * test set scores: [opusTCv20210807_transformer-big_2022-06-23.eval.txt](https://object.pouta.csc.fi/Tat | ||
| oeba-MT-models/spa-fin/opusTCv20210807_transformer-big_2022-06-23.eval.txt) | ||
|
|
||
| ## Benchmarks | ||
|
|
||
| | testset | BLEU | chr-F | #sent | #words | BP | | ||
| |---------|-------|-------|-------|--------|----| | ||
| | Tatoeba-test-v2021-08-07.spa-fin | 45.2 | 0.67442 | 2513 | 14131 | 0.950 | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,19 @@ | ||
| # opusTCv20210807_transformer-big_2022-06-23.zip | ||
|
|
||
| * dataset: opusTCv20210807 | ||
| * model: transformer-big | ||
| * source language(s): tur | ||
| * target language(s): deu | ||
| * raw source language(s): tur | ||
| * raw target language(s): deu | ||
| * model: transformer-big | ||
| * pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| * download: [opusTCv20210807_transformer-big_2022-06-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/tur-deu/opusTCv20210807_transformer-big_2022-06-23.zip) | ||
| * test set translations: [opusTCv20210807_transformer-big_2022-06-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/tur-deu/opusTCv20210807_transformer-big_2022-06-23.test.txt) | ||
| * test set scores: [opusTCv20210807_transformer-big_2022-06-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/tur-deu/opusTCv20210807_transformer-big_2022-06-23.eval.txt) | ||
|
|
||
| ## Benchmarks | ||
|
|
||
| | testset | BLEU | chr-F | #sent | #words | BP | | ||
| |---------|-------|-------|-------|--------|----| | ||
| | Tatoeba-test-v2021-08-07.tur-deu | 45.1 | 0.64137 | 5000 | 39079 | 0.946 | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,30 @@ | ||
| # opusTCv20210807_transformer-big_2022-06-24.zip | ||
|
|
||
| * dataset: opusTCv20210807 | ||
| * model: transformer-big | ||
| * source language(s): ces csb csb_Latn dsb hsb pol | ||
| * target language(s): deu | ||
| * raw source language(s): ces csb dsb hsb pol | ||
| * raw target language(s): deu | ||
| * model: transformer-big | ||
| * pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| * download: [opusTCv20210807_transformer-big_2022-06-24.zip](https://object.pouta.csc.fi/Tatoeba-MT-mode | ||
| ls/zlw-deu/opusTCv20210807_transformer-big_2022-06-24.zip) | ||
| * test set translations: [opusTCv20210807_transformer-big_2022-06-24.test.txt](https://object.pouta.csc. | ||
| fi/Tatoeba-MT-models/zlw-deu/opusTCv20210807_transformer-big_2022-06-24.test.txt) | ||
| * test set scores: [opusTCv20210807_transformer-big_2022-06-24.eval.txt](https://object.pouta.csc.fi/Tat | ||
| oeba-MT-models/zlw-deu/opusTCv20210807_transformer-big_2022-06-24.eval.txt) | ||
|
|
||
| ## Benchmarks | ||
|
|
||
| | testset | BLEU | chr-F | #sent | #words | BP | | ||
| |---------|-------|-------|-------|--------|----| | ||
| | newssyscomb2009.ces-deu | 24.8 | 0.54383 | 502 | 11271 | 0.974 | | ||
| | news-test2008.ces-deu | 23.6 | 0.54025 | 2051 | 47427 | 0.987 | | ||
| | newstest2009.ces-deu | 24.5 | 0.54317 | 2525 | 62816 | 0.982 | | ||
| | newstest2010.ces-deu | 25.6 | 0.55397 | 2489 | 61511 | 0.959 | | ||
| | newstest2011.ces-deu | 24.4 | 0.53711 | 3003 | 72981 | 0.995 | | ||
| | newstest2012.ces-deu | 25.6 | 0.54185 | 3003 | 72886 | 0.995 | | ||
| | newstest2013.ces-deu | 27.7 | 0.55989 | 3000 | 63737 | 1.000 | | ||
| | newstest2019-csde.ces-deu | 26.1 | 0.54920 | 1997 | 48969 | 0.992 | | ||
| | Tatoeba-test-v2021-08-07.multi-deu | 50.4 | 0.67943 | 9824 | 74086 | 0.986 | |