-
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
67 changed files
with
2,478 additions
and
9 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
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 @@ | ||
| opusTCv20210807_transformer-big_2022-07-22.yml |
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 @@ | ||
| opusTCv20210807_transformer-big_2022-07-23.yml |
66 changes: 66 additions & 0 deletions
66
models/bat-gmq/opusTCv20210807_transformer-big_2022-07-23.yml
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 +1,66 @@ | ||
| release: bat-gmq/opusTCv20210807_transformer-big_2022-07-23.zip | ||
| release-date: 2022-07-23 | ||
| dataset-name: opusTCv20210807 | ||
| modeltype: transformer-big | ||
| vocabulary: | ||
| source: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| target: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| subwords: | ||
| source: spm32k | ||
| target: spm32k | ||
| subword-models: | ||
| source: source.spm | ||
| target: target.spm | ||
| source-languages: | ||
| - lav | ||
| - lit | ||
| - ltg | ||
| target-languages: | ||
| - dan | ||
| - isl | ||
| - swe | ||
| raw-source-languages: | ||
| - lav | ||
| - lit | ||
| - ltg | ||
| raw-target-languages: | ||
| - dan | ||
| - isl | ||
| - swe | ||
| use-target-labels: | ||
| training-data: | ||
| lav-dan: Tatoeba-train-v2021-08-07.dan-lav.strict (16721223) | ||
| lav-isl: Tatoeba-train-v2021-08-07.isl-lav.strict (1845675) | ||
| lav-swe: Tatoeba-train-v2021-08-07.lav-swe.strict (17135312) | ||
| lit-swe: Tatoeba-train-v2021-08-07.lit-swe.strict (19167587) | ||
| ltg-dan: Tatoeba-train-v2021-08-07.dan-ltg.strict (5352) | ||
| ltg-isl: Tatoeba-train-v2021-08-07.isl-ltg.strict (4740) | ||
| ltg-swe: Tatoeba-train-v2021-08-07.ltg-swe.strict (259) | ||
| validation-data: | ||
| dan-lav: Tatoeba-dev-v2021-08-07, 999 | ||
| isl-lav: Tatoeba-dev-v2021-08-07, 997 | ||
| lav-swe: Tatoeba-dev-v2021-08-07, 1000 | ||
| lit-swe: Tatoeba-dev-v2021-08-07, 1000 | ||
| dan-ltg: Tatoeba-dev-v2021-08-07, 1 | ||
| isl-ltg: Tatoeba-dev-v2021-08-07, 3 | ||
| total-size-shuffled: 3972 | ||
| devset-selected: top 3972 lines of Tatoeba-dev-v2021-08-07.src.shuffled | ||
| test-data: | ||
| Tatoeba-test-v2021-08-07.lav-dan: 1/22 | ||
| Tatoeba-test-v2021-08-07.lav-isl: 1/22 | ||
| Tatoeba-test-v2021-08-07.lav-swe: 1/22 | ||
| Tatoeba-test-v2021-08-07.lit-swe: 1/6 | ||
| Tatoeba-test-v2021-08-07.multi-multi: 4/72 | ||
| BLEU-scores: | ||
| Tatoeba-test-v2021-08-07.lav-dan: 11.6 | ||
| Tatoeba-test-v2021-08-07.lav-isl: 35.8 | ||
| Tatoeba-test-v2021-08-07.lav-swe: 19.7 | ||
| Tatoeba-test-v2021-08-07.lit-swe: 100.0 | ||
| Tatoeba-test-v2021-08-07.multi-multi: 20.1 | ||
| chr-F-scores: | ||
| Tatoeba-test-v2021-08-07.lav-dan: 0.29314 | ||
| Tatoeba-test-v2021-08-07.lav-isl: 0.46242 | ||
| Tatoeba-test-v2021-08-07.lav-swe: 0.51192 | ||
| Tatoeba-test-v2021-08-07.lit-swe: 10.00000 | ||
| Tatoeba-test-v2021-08-07.multi-multi: 0.46168 |
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 @@ | ||
| opusTCv20210807_transformer-big_2022-07-23.yml |
105 changes: 105 additions & 0 deletions
105
models/bat-itc/opusTCv20210807_transformer-big_2022-07-23.yml
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 +1,105 @@ | ||
| release: bat-itc/opusTCv20210807_transformer-big_2022-07-23.zip | ||
| release-date: 2022-07-23 | ||
| dataset-name: opusTCv20210807 | ||
| modeltype: transformer-big | ||
| vocabulary: | ||
| source: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| target: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| subwords: | ||
| source: spm32k | ||
| target: spm32k | ||
| subword-models: | ||
| source: source.spm | ||
| target: target.spm | ||
| source-languages: | ||
| - lav | ||
| - lit | ||
| - ltg | ||
| - prg_Latn | ||
| - sgs | ||
| target-languages: | ||
| - cat | ||
| - fra | ||
| - glg | ||
| - ita | ||
| - lat_Latn | ||
| - pob | ||
| - por | ||
| - spa | ||
| raw-source-languages: | ||
| - lav | ||
| - lit | ||
| - ltg | ||
| - prg | ||
| - sgs | ||
| raw-target-languages: | ||
| - cat | ||
| - fra | ||
| - glg | ||
| - ita | ||
| - lat | ||
| - pob | ||
| - por | ||
| - spa | ||
| use-target-labels: | ||
| validation-data: | ||
| fra-lav: Tatoeba-dev-v2021-08-07, 998 | ||
| ita-lav: Tatoeba-dev-v2021-08-07, 1000 | ||
| lav-spa: Tatoeba-dev-v2021-08-07, 998 | ||
| cat-lit: Tatoeba-dev-v2021-08-07, 1000 | ||
| fra-lit: Tatoeba-dev-v2021-08-07, 934 | ||
| glg-lit: Tatoeba-dev-v2021-08-07, 1000 | ||
| ita-lit: Tatoeba-dev-v2021-08-07, 942 | ||
| lit-pob: Tatoeba-dev-v2021-08-07, 90 | ||
| lit-por: Tatoeba-dev-v2021-08-07, 910 | ||
| lit-spa: Tatoeba-dev-v2021-08-07, 943 | ||
| fra-ltg: Tatoeba-dev-v2021-08-07, 2 | ||
| ltg-spa: Tatoeba-dev-v2021-08-07, 2 | ||
| total-size-shuffled: 8791 | ||
| devset-selected: top 5000 lines of Tatoeba-dev-v2021-08-07.src.shuffled | ||
| test-data: | ||
| Tatoeba-test-v2021-08-07.lav-fra: 36/191 | ||
| Tatoeba-test-v2021-08-07.lav-ita: 21/108 | ||
| Tatoeba-test-v2021-08-07.lav-spa: 58/344 | ||
| Tatoeba-test-v2021-08-07.lit-cat: 1/6 | ||
| Tatoeba-test-v2021-08-07.lit-fra: 142/1036 | ||
| Tatoeba-test-v2021-08-07.lit-glg: 1/6 | ||
| Tatoeba-test-v2021-08-07.lit-ita: 224/1505 | ||
| Tatoeba-test-v2021-08-07.lit-lat: 4/17 | ||
| Tatoeba-test-v2021-08-07.lit-por: 73/514 | ||
| Tatoeba-test-v2021-08-07.lit-spa: 454/2751 | ||
| Tatoeba-test-v2021-08-07.multi-multi: 1012/6466 | ||
| Tatoeba-test-v2021-08-07.prg-fra: 13/104 | ||
| Tatoeba-test-v2021-08-07.prg-spa: 24/175 | ||
| Tatoeba-test-v2021-08-07.sgs-spa: 2/5 | ||
| BLEU-scores: | ||
| Tatoeba-test-v2021-08-07.lav-fra: 30.2 | ||
| Tatoeba-test-v2021-08-07.lav-ita: 26.9 | ||
| Tatoeba-test-v2021-08-07.lav-spa: 20.8 | ||
| Tatoeba-test-v2021-08-07.lit-cat: 5.5 | ||
| Tatoeba-test-v2021-08-07.lit-fra: 19.9 | ||
| Tatoeba-test-v2021-08-07.lit-glg: 9.7 | ||
| Tatoeba-test-v2021-08-07.lit-ita: 18.0 | ||
| Tatoeba-test-v2021-08-07.lit-lat: 2.9 | ||
| Tatoeba-test-v2021-08-07.lit-por: 22.5 | ||
| Tatoeba-test-v2021-08-07.lit-spa: 25.5 | ||
| Tatoeba-test-v2021-08-07.multi-multi: 22.8 | ||
| Tatoeba-test-v2021-08-07.prg-fra: 0.8 | ||
| Tatoeba-test-v2021-08-07.prg-spa: 0.4 | ||
| Tatoeba-test-v2021-08-07.sgs-spa: 0.0 | ||
| chr-F-scores: | ||
| Tatoeba-test-v2021-08-07.lav-fra: 0.46469 | ||
| Tatoeba-test-v2021-08-07.lav-ita: 0.41275 | ||
| Tatoeba-test-v2021-08-07.lav-spa: 0.45169 | ||
| Tatoeba-test-v2021-08-07.lit-cat: 0.21680 | ||
| Tatoeba-test-v2021-08-07.lit-fra: 0.41453 | ||
| Tatoeba-test-v2021-08-07.lit-glg: 0.13250 | ||
| Tatoeba-test-v2021-08-07.lit-ita: 0.40197 | ||
| Tatoeba-test-v2021-08-07.lit-lat: 0.12399 | ||
| Tatoeba-test-v2021-08-07.lit-por: 0.41762 | ||
| Tatoeba-test-v2021-08-07.lit-spa: 0.45980 | ||
| Tatoeba-test-v2021-08-07.multi-multi: 0.43709 | ||
| Tatoeba-test-v2021-08-07.prg-fra: 0.12353 | ||
| Tatoeba-test-v2021-08-07.prg-spa: 0.13449 | ||
| Tatoeba-test-v2021-08-07.sgs-spa: 0.11209 |
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 @@ | ||
| opusTCv20210807_transformer-big_2022-07-22.yml |
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 @@ | ||
| opusTCv20210807_transformer-big_2022-07-22.yml |
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 @@ | ||
| opusTCv20210807_transformer-big_2022-07-23.yml |
34 changes: 34 additions & 0 deletions
34
models/deu-sqi/opusTCv20210807_transformer-big_2022-07-23.yml
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 +1,34 @@ | ||
| release: deu-sqi/opusTCv20210807_transformer-big_2022-07-23.zip | ||
| release-date: 2022-07-23 | ||
| dataset-name: opusTCv20210807 | ||
| modeltype: transformer-big | ||
| vocabulary: | ||
| source: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| target: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| subwords: | ||
| source: spm32k | ||
| target: spm32k | ||
| subword-models: | ||
| source: source.spm | ||
| target: target.spm | ||
| source-languages: | ||
| - deu | ||
| target-languages: | ||
| - sqi | ||
| raw-source-languages: | ||
| - deu | ||
| raw-target-languages: | ||
| - sqi | ||
| training-data: | ||
| deu-sqi: Tatoeba-train-v2021-08-07.deu-sqi.strict (11647962) | ||
| validation-data: | ||
| deu-sqi: Tatoeba-dev-v2021-08-07, 1000 | ||
| total-size-shuffled: 1000 | ||
| devset-selected: top 1000 lines of Tatoeba-dev-v2021-08-07.src.shuffled | ||
| test-data: | ||
| Tatoeba-test-v2021-08-07.deu-sqi: 1/6 | ||
| BLEU-scores: | ||
| Tatoeba-test-v2021-08-07.deu-sqi: 76.0 | ||
| chr-F-scores: | ||
| Tatoeba-test-v2021-08-07.deu-sqi: 0.87955 |
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 @@ | ||
| opusTCv20210807_transformer-big_2022-07-23.yml |
42 changes: 42 additions & 0 deletions
42
models/eus-gmq/opusTCv20210807_transformer-big_2022-07-23.yml
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 +1,42 @@ | ||
| release: eus-gmq/opusTCv20210807_transformer-big_2022-07-23.zip | ||
| release-date: 2022-07-23 | ||
| dataset-name: opusTCv20210807 | ||
| modeltype: transformer-big | ||
| vocabulary: | ||
| source: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| target: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| subwords: | ||
| source: spm32k | ||
| target: spm32k | ||
| subword-models: | ||
| source: source.spm | ||
| target: target.spm | ||
| source-languages: | ||
| - eus | ||
| target-languages: | ||
| - nno | ||
| - nob | ||
| raw-source-languages: | ||
| - eus | ||
| raw-target-languages: | ||
| - nno | ||
| - nob | ||
| use-target-labels: | ||
| training-data: | ||
| eus-nno: Tatoeba-train-v2021-08-07.eus-nno.strict (533000) | ||
| eus-nob: Tatoeba-train-v2021-08-07.eus-nob.strict (1484824) | ||
| validation-data: | ||
| eus-nno: Tatoeba-dev-v2021-08-07, 261 | ||
| eus-nob: Tatoeba-dev-v2021-08-07, 739 | ||
| total-size-shuffled: 995 | ||
| devset-selected: top 995 lines of Tatoeba-dev-v2021-08-07.src.shuffled | ||
| test-data: | ||
| Tatoeba-test-v2021-08-07.eus-nor: 6/52 | ||
| Tatoeba-test-v2021-08-07.eus-multi: 6/52 | ||
| BLEU-scores: | ||
| Tatoeba-test-v2021-08-07.eus-nor: 28.1 | ||
| Tatoeba-test-v2021-08-07.eus-multi: 28.0 | ||
| chr-F-scores: | ||
| Tatoeba-test-v2021-08-07.eus-nor: 0.43894 | ||
| Tatoeba-test-v2021-08-07.eus-multi: 0.43460 |
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 @@ | ||
| opusTCv20210807_transformer-big_2022-07-23.yml |
75 changes: 75 additions & 0 deletions
75
models/eus-itc/opusTCv20210807_transformer-big_2022-07-23.yml
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 +1,75 @@ | ||
| release: eus-itc/opusTCv20210807_transformer-big_2022-07-23.zip | ||
| release-date: 2022-07-23 | ||
| dataset-name: opusTCv20210807 | ||
| modeltype: transformer-big | ||
| vocabulary: | ||
| source: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| target: opusTCv20210807.spm32k-spm32k.vocab.yml | ||
| pre-processing: normalization + SentencePiece (spm32k,spm32k) | ||
| subwords: | ||
| source: spm32k | ||
| target: spm32k | ||
| subword-models: | ||
| source: source.spm | ||
| target: target.spm | ||
| source-languages: | ||
| - eus | ||
| target-languages: | ||
| - fra | ||
| - ita | ||
| - lat_Latn | ||
| - mwl | ||
| - pob | ||
| - por | ||
| - spa | ||
| raw-source-languages: | ||
| - eus | ||
| raw-target-languages: | ||
| - fra | ||
| - ita | ||
| - lat | ||
| - mwl | ||
| - pob | ||
| - por | ||
| - spa | ||
| use-target-labels: | ||
| training-data: | ||
| eus-fra: Tatoeba-train-v2021-08-07.eus-fra.strict (1535891) | ||
| eus-ita: Tatoeba-train-v2021-08-07.eus-ita.strict (3136335) | ||
| eus-mwl: Tatoeba-train-v2021-08-07.eus-mwl.strict (2763) | ||
| eus-pob: Tatoeba-train-v2021-08-07.eus-pob.strict (750313) | ||
| eus-por: Tatoeba-train-v2021-08-07.eus-por.strict (3047546) | ||
| eus-spa: Tatoeba-train-v2021-08-07.eus-spa.strict (13354717) | ||
| validation-data: | ||
| eus-fra: Tatoeba-dev-v2021-08-07, 876 | ||
| eus-ita: Tatoeba-dev-v2021-08-07, 1000 | ||
| eus-mwl: Tatoeba-dev-v2021-08-07, 1000 | ||
| eus-pob: Tatoeba-dev-v2021-08-07, 186 | ||
| eus-por: Tatoeba-dev-v2021-08-07, 814 | ||
| eus-spa: Tatoeba-dev-v2021-08-07, 992 | ||
| total-size-shuffled: 4867 | ||
| devset-selected: top 4867 lines of Tatoeba-dev-v2021-08-07.src.shuffled | ||
| test-data: | ||
| Tatoeba-test-v2021-08-07.eus-fra: 144/1013 | ||
| Tatoeba-test-v2021-08-07.eus-ita: 62/412 | ||
| Tatoeba-test-v2021-08-07.eus-lat: 1/16 | ||
| Tatoeba-test-v2021-08-07.eus-mwl: 1/4 | ||
| Tatoeba-test-v2021-08-07.eus-por: 1/6 | ||
| Tatoeba-test-v2021-08-07.eus-spa: 1850/12465 | ||
| Tatoeba-test-v2021-08-07.eus-multi: 2058/13904 | ||
| BLEU-scores: | ||
| Tatoeba-test-v2021-08-07.eus-fra: 35.1 | ||
| Tatoeba-test-v2021-08-07.eus-ita: 48.0 | ||
| Tatoeba-test-v2021-08-07.eus-lat: 2.1 | ||
| Tatoeba-test-v2021-08-07.eus-mwl: 9.7 | ||
| Tatoeba-test-v2021-08-07.eus-por: 100.0 | ||
| Tatoeba-test-v2021-08-07.eus-spa: 49.5 | ||
| Tatoeba-test-v2021-08-07.eus-multi: 49.3 | ||
| chr-F-scores: | ||
| Tatoeba-test-v2021-08-07.eus-fra: 0.55642 | ||
| Tatoeba-test-v2021-08-07.eus-ita: 0.65291 | ||
| Tatoeba-test-v2021-08-07.eus-lat: 0.13899 | ||
| Tatoeba-test-v2021-08-07.eus-mwl: 0.23196 | ||
| Tatoeba-test-v2021-08-07.eus-por: 10.00000 | ||
| Tatoeba-test-v2021-08-07.eus-spa: 0.67352 | ||
| Tatoeba-test-v2021-08-07.eus-multi: 0.67092 |
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 @@ | ||
| opusTCv20210807_transformer-big_2022-07-23.yml |
Oops, something went wrong.