Initial commit

README.md

@@ -0,0 +1,63 @@
+---
+language:
+- en
+- ja
+
+tags:
+- translation
+
+license: apache-2.0
+---
+### en-ja
+
+* source group: English 
+* target group: Japanese 
+*  OPUS readme: [eng-jpn](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-jpn/README.md)
+
+*  model: transformer-align
+* source language(s): eng
+* target language(s): jpn
+* model: transformer-align
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus+bt-2021-04-10.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-jpn/opus+bt-2021-04-10.zip)
+* test set translations: [opus+bt-2021-04-10.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-jpn/opus+bt-2021-04-10.test.txt)
+* test set scores: [opus+bt-2021-04-10.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-jpn/opus+bt-2021-04-10.eval.txt)
+
+## Benchmarks
+
+| testset | BLEU  | chr-F | #sent | #words | BP |
+|---------|-------|-------|-------|--------|----|
+| Tatoeba-test.eng-jpn 	| 15.2 	| 0.258 	| 10000 	| 99206 	| 1.000 |
+
+
+### System Info: 
+- hf_name: en-ja
+- source_languages: eng
+- target_languages: jpn
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-jpn/README.md
+- original_repo: Tatoeba-Challenge
+- tags: ['translation']
+- languages: ['en', 'ja']
+- src_constituents: ('English', {'eng'})
+- tgt_constituents: ('Japanese', {'jpn', 'jpn_Latn', 'jpn_Yiii', 'jpn_Kana', 'jpn_Hira', 'jpn_Hang', 'jpn_Bopo', 'jpn_Hani'})
+- src_multilingual: False
+- tgt_multilingual: False
+- long_pair: eng-jpn
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-jpn/opus+bt-2021-04-10.zip
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-jpn/opus+bt-2021-04-10.test.txt
+- src_alpha3: eng
+- tgt_alpha3: jpn
+- chrF2_score: 0.258
+- bleu: 15.2
+- src_name: English
+- tgt_name: Japanese
+- train_date: 2021-04-10 00:00:00
+- src_alpha2: en
+- tgt_alpha2: ja
+- prefer_old: False
+- short_pair: en-ja
+- helsinki_git_sha: 70b0a9621f054ef1d8ea81f7d55595d7f64d19ff
+- transformers_git_sha: 12b4d66a80419db30a15e7b9d4208ceb9887c03b
+- port_machine: LM0-400-22516.local
+- port_time: 2021-10-12-11:13

config.json

@@ -0,0 +1,43 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 65000,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 65000,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 65001
+}

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"en-ja","source_languages":"eng","target_languages":"jpn","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/eng-jpn\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["en","ja"],"src_constituents":["English",["eng"]],"tgt_constituents":["Japanese",["jpn","jpn_Latn","jpn_Yiii","jpn_Kana","jpn_Hira","jpn_Hang","jpn_Bopo","jpn_Hani"]],"src_multilingual":false,"tgt_multilingual":false,"long_pair":"eng-jpn","prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-jpn\/opus+bt-2021-04-10.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-jpn\/opus+bt-2021-04-10.test.txt","src_alpha3":"eng","tgt_alpha3":"jpn","chrF2_score":0.258,"bleu":15.2,"src_name":"English","tgt_name":"Japanese","train_date":1618012800000,"src_alpha2":"en","tgt_alpha2":"ja","prefer_old":false,"short_pair":"en-ja","helsinki_git_sha":"70b0a9621f054ef1d8ea81f7d55595d7f64d19ff","transformers_git_sha":"12b4d66a80419db30a15e7b9d4208ceb9887c03b","port_machine":"LM0-400-22516.local","port_time":"2021-10-12-11:13"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1211116eb4e023ae2955078481f0a9921bf33f4b62934dd917acd8db1158be8
+size 221610115

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "eng", "target_lang": "jpn", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "marian_ckpt/eng-jpn", "tokenizer_class": "MarianTokenizer"}