Initial commit

README.md

@@ -0,0 +1,67 @@
+---
+language:
+- en
+- ro
+
+tags:
+- translation
+
+license: apache-2.0
+---
+### en-ro
+
+* source group: English 
+* target group: Romanian 
+*  OPUS readme: [eng-ron](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-ron/README.md)
+
+*  model: transformer-align
+* source language(s): eng
+* target language(s): mol ron
+* model: transformer-align
+* 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 original weights: [opus+bt-2021-03-07.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-ron/opus+bt-2021-03-07.zip)
+* test set translations: [opus+bt-2021-03-07.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-ron/opus+bt-2021-03-07.test.txt)
+* test set scores: [opus+bt-2021-03-07.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-ron/opus+bt-2021-03-07.eval.txt)
+
+## Benchmarks
+
+| testset | BLEU  | chr-F | #sent | #words | BP |
+|---------|-------|-------|-------|--------|----|
+| newsdev2016-enro.eng-ron 	| 33.5 	| 0.610 	| 1999 	| 51566 	| 0.984 |
+| newstest2016-enro.eng-ron 	| 31.7 	| 0.591 	| 1999 	| 49094 	| 0.998 |
+| Tatoeba-test.eng-ron 	| 46.9 	| 0.678 	| 5000 	| 36851 	| 0.983 |
+
+
+### System Info: 
+- hf_name: en-ro
+- source_languages: eng
+- target_languages: ron
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-ron/README.md
+- original_repo: Tatoeba-Challenge
+- tags: ['translation']
+- languages: ['en', 'ro']
+- src_constituents: ('English', {'eng'})
+- tgt_constituents: ('Romanian', {'ron'})
+- src_multilingual: False
+- tgt_multilingual: False
+- long_pair: eng-ron
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-ron/opus+bt-2021-03-07.zip
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-ron/opus+bt-2021-03-07.test.txt
+- src_alpha3: eng
+- tgt_alpha3: ron
+- chrF2_score: 0.678
+- bleu: 46.9
+- src_name: English
+- tgt_name: Romanian
+- train_date: 2021-03-07 00:00:00
+- src_alpha2: en
+- tgt_alpha2: ro
+- prefer_old: False
+- short_pair: en-ro
+- helsinki_git_sha: 2ef219d5b67f0afb0c6b732cd07001d84181f002
+- transformers_git_sha: 12b4d66a80419db30a15e7b9d4208ceb9887c03b
+- port_machine: LM0-400-22516.local
+- port_time: 2021-11-08-09:31

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-ro","source_languages":"eng","target_languages":"ron","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/eng-ron\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["en","ro"],"src_constituents":["English",["eng"]],"tgt_constituents":["Romanian",["ron"]],"src_multilingual":false,"tgt_multilingual":false,"long_pair":"eng-ron","prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-ron\/opus+bt-2021-03-07.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-ron\/opus+bt-2021-03-07.test.txt","src_alpha3":"eng","tgt_alpha3":"ron","chrF2_score":0.678,"bleu":46.9,"src_name":"English","tgt_name":"Romanian","train_date":1615075200000,"src_alpha2":"en","tgt_alpha2":"ro","prefer_old":false,"short_pair":"en-ro","helsinki_git_sha":"2ef219d5b67f0afb0c6b732cd07001d84181f002","transformers_git_sha":"12b4d66a80419db30a15e7b9d4208ceb9887c03b","port_machine":"LM0-400-22516.local","port_time":"2021-11-08-09:31"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27bef0a4fce2ae1f4bf5408c6c1453e1bc984d1ecdc62e0455488b8fac465987
+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": "ron", "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-ron", "tokenizer_class": "MarianTokenizer"}