Add files using upload-large-folder tool

packages/en_ja/README.md

@@ -0,0 +1,38 @@
+# English-Japanese
+
+Data compiled by [Opus](https://opus.nlpl.eu/).
+
+Dictionary data from Wiktionary using [Wiktextract](https://github.com/tatuylonen/wiktextract).
+
+Includes pretrained models from [Stanza](https://github.com/stanfordnlp/stanza/).
+
+Credits:
+@inproceedings{elkishky_ccaligned_2020,
+ author = {El-Kishky, Ahmed and Chaudhary, Vishrav and Guzmán, Francisco and Koehn, Philipp},
+ booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)},
+ month = {November},
+ title = {{CCAligned}: A Massive Collection of Cross-lingual Web-Document Pairs},
+ year = {2020}
+ address = "Online",
+ publisher = "Association for Computational Linguistics",
+ url = "https://www.aclweb.org/anthology/2020.emnlp-main.480",
+ doi = "10.18653/v1/2020.emnlp-main.480",
+ pages = "5960--5969"
+ }
+
+Holger Schwenk, Vishrav Chaudhary, Shuo Sun, Hongyu Gong and Paco Guzman, WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia, arXiv, July 11 2019.
+
+@inproceedings{elkishky_ccaligned_2020,
+ author = {El-Kishky, Ahmed and Chaudhary, Vishrav and Guzmán, Francisco and Koehn, Philipp},
+ booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)},
+ month = {November},
+ title = {{CCAligned}: A Massive Collection of Cross-lingual Web-Document Pairs},
+ year = {2020}
+ address = "Online",
+ publisher = "Association for Computational Linguistics",
+ url = "https://www.aclweb.org/anthology/2020.emnlp-main.480",
+ doi = "10.18653/v1/2020.emnlp-main.480",
+ pages = "5960--5969"
+ }
+
+P. Lison and J. Tiedemann, 2016, OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016)

packages/en_ja/metadata.json

@@ -0,0 +1,8 @@
+{
+    "package_version": "1.1",
+    "argos_version": "1.1",
+    "from_code": "en",
+    "from_name": "English",
+    "to_code": "ja",
+    "to_name": "Japanese"
+}

packages/en_pt/README.md

@@ -0,0 +1,6 @@
+# English-Portuguese
+
+Trained on data from Opus (EUbookshop, OpenSubtitles, ParaCrawl, WikiMatrix)
+
+Includes pretrained models from [Stanza](https://github.com/stanfordnlp/stanza/blob/master/LICENSE).
+

packages/en_pt/metadata.json

@@ -0,0 +1,8 @@
+{
+    "package_version": "1.0",
+    "argos_version": "1.0",
+    "from_code": "en",
+    "from_name": "English",
+    "to_code": "pt",
+    "to_name": "Portuguese"
+}

packages/en_ur/README.md

@@ -0,0 +1,11 @@
+# English - Urdu version 1.9
+
+Authors: Jörg Tiedemann and Santhosh Thottingal
+Title: "OPUS-MT — Building open translation services for the World"
+Book Title: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation (EAMT)
+Year: 2020
+Location: Lisbon, Portugal
+
+The original OPUS model from which this packaged model is derived is licensed CC-BY 4.0
+
+https://community.libretranslate.com/t/opus-mt-language-models-port-thread/757/

packages/en_ur/metadata.json

@@ -0,0 +1 @@
+{"package_version": "1.9", "argos_version": "1.9", "from_code": "en", "from_name": "English", "to_code": "ur", "to_name": "Urdu"}

packages/ko_en/README.md

@@ -0,0 +1,27 @@
+# Korean-English
+
+Data compiled by [Opus](https://opus.nlpl.eu/).
+
+Dictionary data from Wiktionary using [Wiktextract](https://github.com/tatuylonen/wiktextract).
+
+Includes pretrained models from [Stanza](https://github.com/stanfordnlp/stanza/).
+
+Credits:
+ @inproceedings{elkishky_ccaligned_2020,
+ author = {El-Kishky, Ahmed and Chaudhary, Vishrav and Guzmán, Francisco and Koehn, Philipp},
+ booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)},
+ month = {November},
+ title = {{CCAligned}: A Massive Collection of Cross-lingual Web-Document Pairs},
+ year = {2020}
+ address = "Online",
+ publisher = "Association for Computational Linguistics",
+ url = "https://www.aclweb.org/anthology/2020.emnlp-main.480",
+ doi = "10.18653/v1/2020.emnlp-main.480",
+ pages = "5960--5969"
+ }
+
+Holger Schwenk, Vishrav Chaudhary, Shuo Sun, Hongyu Gong and Paco Guzman, WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia, arXiv, July 11 2019.
+
+P. Lison and J. Tiedemann, 2016, OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016)
+
+

packages/ko_en/metadata.json

@@ -0,0 +1,8 @@
+{
+    "package_version": "1.1",
+    "argos_version": "1.1",
+    "from_code": "ko",
+    "from_name": "Korean",
+    "to_code": "en",
+    "to_name": "English"
+}

packages/pt_en/README.md

@@ -0,0 +1,6 @@
+# Portuguese-English
+
+Trained on data from Opus (EUbookshop, OpenSubtitles, ParaCrawl, WikiMatrix)
+
+Includes pretrained models from [Stanza](https://github.com/stanfordnlp/stanza/blob/master/LICENSE).
+

packages/pt_en/metadata.json

@@ -0,0 +1,8 @@
+{
+    "package_version": "1.0",
+    "argos_version": "1.0",
+    "from_code": "pt",
+    "from_name": "Portuguese",
+    "to_code": "en",
+    "to_name": "English"
+}

packages/translate-bg_en-1_9/README.md

@@ -0,0 +1,10 @@
+# Bulgarian - English version 1.9
+
+Authors: Jörg Tiedemann and Santhosh Thottingal
+Title: "OPUS-MT — Building open translation services for the World"
+Book Title: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation (EAMT)
+Year: 2020
+Location: Lisbon, Portugal
+
+The original OPUS model from which this packaged model is derived is licensed CC-BY 4.0
+

packages/translate-bg_en-1_9/metadata.json

@@ -0,0 +1 @@
+{"package_version": "1.9", "argos_version": "1.9.0", "from_code": "bg", "from_name": "Bulgarian", "to_code": "en", "to_name": "English"}

packages/translate-bg_en-1_9/model/config.json

@@ -0,0 +1,9 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": true,
+  "bos_token": "<s>",
+  "decoder_start_token": "<s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": null,
+  "unk_token": "<unk>"
+}

packages/translate-cs_en-1_9_6/README.md

@@ -0,0 +1,9 @@
+# Czech - English version 1.0
+
+Authors: Jörg Tiedemann and Santhosh Thottingal
+Title: "OPUS-MT — Building open translation services for the World"
+Book Title: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation (EAMT)
+Year: 2020
+Location: Lisbon, Portugal
+
+The original OPUS model from which this packaged model is derived is licensed CC-BY 4.0

packages/translate-cs_en-1_9_6/metadata.json

@@ -0,0 +1,8 @@
+{
+    "package_version": "1.9.6",
+    "argos_version": "1.9.6",
+    "from_code": "cs",
+    "from_name": "Czech",
+    "to_code": "en",
+    "to_name": "English"
+}

packages/translate-cs_en-1_9_6/model/config.json

@@ -0,0 +1,10 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": true,
+  "bos_token": "<s>",
+  "decoder_start_token": "<s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": null,
+  "multi_query_attention": false,
+  "unk_token": "<unk>"
+}

packages/translate-en_bg-1_9/model/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08e1b6aab7d313aa62b49875a67e2dbcf54a47bcbc904bd5fe9d31d02ff499a
+size 81055558

packages/translate-en_sl-1_9/README.md

@@ -0,0 +1,10 @@
+# English - Slovenian version 1.9
+
+Authors: Jörg Tiedemann and Santhosh Thottingal
+Title: "OPUS-MT — Building open translation services for the World"
+Book Title: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation (EAMT)
+Year: 2020
+Location: Lisbon, Portugal
+
+The original OPUS model from which this packaged model is derived is licensed CC-BY 4.0
+

packages/translate-en_sl-1_9/metadata.json

@@ -0,0 +1 @@
+{"package_version": "1.9", "argos_version": "1.9.0", "from_code": "en", "from_name": "English", "to_code": "sl", "to_name": "Slovenian"}

packages/translate-en_sl-1_9/model/config.json

@@ -0,0 +1,9 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": true,
+  "bos_token": "<s>",
+  "decoder_start_token": "<s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": null,
+  "unk_token": "<unk>"
+}

packages/translate-en_tr-1_5/README.md

@@ -0,0 +1,30 @@
+# English-Turkish
+
+Data compiled by [Opus](https://opus.nlpl.eu/).
+
+Dictionary data from Wiktionary using [Wiktextract](https://github.com/tatuylonen/wiktextract).
+
+Includes pretrained models from [Stanza](https://github.com/stanfordnlp/stanza/).
+
+Credits:
+
+El-Kishky, Ahmed and Chaudhary, Vishrav and Guzmn, Francisco and Koehn, Philipp - Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
+
+Holger Schwenk, Guillaume Wenzek, Sergey Edunov, Edouard Grave, Armand Joulin and Angela Fan, CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB
+
+gourmet project at https://gourmet-project.eu
+
+J. Tiedemann, 2012, Parallel Data, Tools and Interfaces in OPUS. In Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012)
+
+J. Tiedemann, 2012, Parallel Data, Tools and Interfaces in OPUS. In Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012)
+
+Reimers, Nils and Gurevych, Iryna - Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation
+
+Holger Schwenk, Vishrav Chaudhary, Shuo Sun, Hongyu Gong and Paco Guzman, WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia, arXiv, July 11 2019.
+
+J. Tiedemann, 2012, Parallel Data, Tools and Interfaces in OPUS. In Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012)
+
+J. Tiedemann, 2012, Parallel Data, Tools and Interfaces in OPUS. In Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012)
+
+El-Kishky, Ahmed and Renduchintala, Adi and Cross, James and Guzmn, Francisco and Koehn, Philipp - {XLEnt}: Mining Cross-lingual Entities with Lexical-Semantic-Phonetic Word Alignment
+

packages/translate-en_tr-1_5/metadata.json

@@ -0,0 +1,8 @@
+{
+    "package_version": "1.5",
+    "argos_version": "1.5",
+    "from_code": "en",
+    "from_name": "English",
+    "to_code": "tr",
+    "to_name": "Turkish"
+}

packages/translate-es_pt-1_0/README.md

@@ -0,0 +1 @@
+# Spanish - Portuguese version 1.0

packages/translate-es_pt-1_0/metadata.json

@@ -0,0 +1 @@
+{"package_version": "1.0", "argos_version": "1.9.0", "from_code": "es", "from_name": "Spanish", "to_code": "pt", "to_name": "Portuguese"}

packages/translate-es_pt-1_0/model/config.json

@@ -0,0 +1,9 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": false,
+  "bos_token": "<s>",
+  "decoder_start_token": "<s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": null,
+  "unk_token": "<unk>"
+}

packages/translate-eu_en-1_9/README.md

@@ -0,0 +1,9 @@
+# Basque-English
+
+Data compiled by [Opus](https://opus.nlpl.eu/).
+
+Dictionary data from Wiktionary using [Wiktextract](https://github.com/tatuylonen/wiktextract).
+
+Includes pretrained models from [Stanza](https://github.com/stanfordnlp/stanza/).
+
+Credits:

packages/translate-eu_en-1_9/metadata.json

@@ -0,0 +1,8 @@
+{
+    "package_version": "1.9",
+    "argos_version": "1.5",
+    "from_code": "eu",
+    "from_name": "Basque",
+    "to_code": "en",
+    "to_name": "English"
+}

packages/translate-eu_en-1_9/model/config.json

@@ -0,0 +1,10 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": false,
+  "bos_token": "<s>",
+  "decoder_start_token": "<s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": null,
+  "multi_query_attention": false,
+  "unk_token": "<unk>"
+}