init

.gitattributes

@@ -1,27 +1,9 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
 *.bin.* filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
-*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zstandard filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,104 @@
----
-license: apache-2.0
----
+---
+language: 
+- en
+- es
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### eng-spa
+
+* source group: English 
+* target group: Spanish 
+*  OPUS readme: [eng-spa](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-spa/README.md)
+
+*  model: transformer
+* source language(s): eng
+* target language(s): spa
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-08-18.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.zip)
+* test set translations: [opus-2020-08-18.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.test.txt)
+* test set scores: [opus-2020-08-18.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| newssyscomb2009-engspa.eng.spa 	| 31.0 	| 0.583 |
+| news-test2008-engspa.eng.spa 	| 29.7 	| 0.564 |
+| newstest2009-engspa.eng.spa 	| 30.2 	| 0.578 |
+| newstest2010-engspa.eng.spa 	| 36.9 	| 0.620 |
+| newstest2011-engspa.eng.spa 	| 38.2 	| 0.619 |
+| newstest2012-engspa.eng.spa 	| 39.0 	| 0.625 |
+| newstest2013-engspa.eng.spa 	| 35.0 	| 0.598 |
+| Tatoeba-test.eng.spa 	| 54.9 	| 0.721 |
+
+
+### System Info: 
+- hf_name: eng-spa
+
+- source_languages: eng
+
+- target_languages: spa
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-spa/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['en', 'es']
+
+- src_constituents: {'eng'}
+
+- tgt_constituents: {'spa'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.test.txt
+
+- src_alpha3: eng
+
+- tgt_alpha3: spa
+
+- short_pair: en-es
+
+- chrF2_score: 0.721
+
+- bleu: 54.9
+
+- brevity_penalty: 0.978
+
+- ref_len: 77311.0
+
+- src_name: English
+
+- tgt_name: Spanish
+
+- train_date: 2020-08-18 00:00:00
+
+- src_alpha2: en
+
+- tgt_alpha2: es
+
+- prefer_old: False
+
+- long_pair: eng-spa
+
+- helsinki_git_sha: d2f0910c89026c34a44e331e785dec1e0faa7b82
+
+- transformers_git_sha: f7af09b4524b784d67ae8526f0e2fcc6f5ed0de9
+
+- port_machine: brutasse
+
+- port_time: 2020-08-24-18:20

config.json

@@ -0,0 +1,59 @@
+{
+    "activation_dropout": 0.0,
+    "activation_function": "swish",
+    "add_bias_logits": false,
+    "add_final_layer_norm": false,
+    "architectures": [
+        "MarianMTModel"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": [
+        [
+            65000
+        ]
+    ],
+    "bos_token_id": 0,
+    "classif_dropout": 0.0,
+    "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,
+    "extra_pos_embeddings": 65001,
+    "force_bos_token_to_be_generated": false,
+    "forced_eos_token_id": 0,
+    "gradient_checkpointing": false,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1",
+        "2": "LABEL_2"
+    },
+    "init_std": 0.02,
+    "is_encoder_decoder": true,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1,
+        "LABEL_2": 2
+    },
+    "max_length": 700,
+    "max_position_embeddings": 700,
+    "model_type": "marian",
+    "normalize_before": false,
+    "normalize_embedding": false,
+    "num_beams": 4,
+    "num_hidden_layers": 6,
+    "pad_token_id": 65000,
+    "scale_embedding": true,
+    "static_position_embeddings": true,
+    "transformers_version": "4.9.0.dev0",
+    "use_cache": true,
+    "vocab_size": 65001
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b5e0865da9b6764e18b637e7c7e34b04be927dc41a1ba97bff23962c2f5857
+size 309944974

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"eng-spa","source_languages":"eng","target_languages":"spa","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/eng-spa\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["en","es"],"src_constituents":["eng"],"tgt_constituents":["spa"],"src_multilingual":false,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-spa\/opus-2020-08-18.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-spa\/opus-2020-08-18.test.txt","src_alpha3":"eng","tgt_alpha3":"spa","short_pair":"en-es","chrF2_score":0.721,"bleu":54.9,"brevity_penalty":0.978,"ref_len":77311.0,"src_name":"English","tgt_name":"Spanish","train_date":1597708800000,"src_alpha2":"en","tgt_alpha2":"es","prefer_old":false,"long_pair":"eng-spa","helsinki_git_sha":"d2f0910c89026c34a44e331e785dec1e0faa7b82","transformers_git_sha":"f7af09b4524b784d67ae8526f0e2fcc6f5ed0de9","port_machine":"brutasse","port_time":"2020-08-24-18:20"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:befce0f620e8e63f83bbb7f0818eb51d541cba28057a7cc14b00466d85c4994c
+size 312087523

tokenizer_config.json

@@ -0,0 +1 @@
+{"target_lang": "spa", "source_lang": "eng"}