Initial commit

README.md

@@ -0,0 +1,89 @@
+---
+language:
+- en
+- fr
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### eng-fra
+
+* source language name: English
+* target language name: French
+* OPUS readme: [README.md](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fra/README.md)
+
+* model: transformer-align
+* source language code: en
+* target language code: fr
+* dataset: opus 
+* release date: 2021-02-22
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2021-02-22.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fra/opus-2021-02-22.zip/eng-fra/opus-2021-02-22.zip)
+* Training data: 
+  * fra-eng: Tatoeba-train (180923857)
+* Validation data: 
+  * eng-fra: Tatoeba-dev, 250098
+  * total-size-shuffled: 249757
+  * devset-selected: top 5000  lines of Tatoeba-dev.src.shuffled!
+* Test data: 
+  * newsdiscussdev2015-enfr.eng-fra: 1500/27986
+  * newsdiscusstest2015-enfr.eng-fra: 1500/28027
+  * newssyscomb2009.eng-fra: 502/12334
+  * news-test2008.eng-fra: 2051/52685
+  * newstest2009.eng-fra: 2525/69278
+  * newstest2010.eng-fra: 2489/66043
+  * newstest2011.eng-fra: 3003/80626
+  * newstest2012.eng-fra: 3003/78011
+  * newstest2013.eng-fra: 3000/70037
+  * Tatoeba-test.eng-fra: 10000/80769
+  * tico19-test.eng-fra: 2100/64655
+* test set translations file: [test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fra/opus-2021-02-22.zip/eng-fra/opus-2021-02-22.test.txt)
+* test set scores file: [eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fra/opus-2021-02-22.zip/eng-fra/opus-2021-02-22.eval.txt)
+* BLEU-scores
+|Test set|score|
+|---|---|
+|Tatoeba-test.eng-fra|50.8|
+|tico19-test.eng-fra|41.8|
+|newsdiscusstest2015-enfr.eng-fra|40.8|
+|newstest2011.eng-fra|34.6|
+|newsdiscussdev2015-enfr.eng-fra|33.9|
+|newstest2013.eng-fra|33.5|
+|newstest2010.eng-fra|33.0|
+|newstest2012.eng-fra|32.0|
+|newssyscomb2009.eng-fra|30.0|
+|newstest2009.eng-fra|29.9|
+|news-test2008.eng-fra|27.5|
+* chr-F-scores
+|Test set|score|
+|---|---|
+|Tatoeba-test.eng-fra|0.671|
+|newsdiscusstest2015-enfr.eng-fra|0.649|
+|tico19-test.eng-fra|0.638|
+|newstest2011.eng-fra|0.614|
+|newsdiscussdev2015-enfr.eng-fra|0.606|
+|newstest2010.eng-fra|0.599|
+|newstest2012.eng-fra|0.593|
+|newstest2013.eng-fra|0.591|
+|newssyscomb2009.eng-fra|0.587|
+|newstest2009.eng-fra|0.58|
+|news-test2008.eng-fra|0.556|
+
+### System Info: 
+* hf_name: eng-fra
+* source_languages: en
+* target_languages: fr
+* opus_readme_url: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fra/opus-2021-02-22.zip/README.md
+* original_repo: Tatoeba-Challenge
+* tags: ['translation']
+* languages: ['en', 'fr']
+* src_constituents: ['eng']
+* tgt_constituents: ['fra']
+* src_multilingual: False
+* tgt_multilingual: False
+* helsinki_git_sha: 6faf2dab0b7b01a0e08a114dbacbb7deac54988d
+* transformers_git_sha: e9a6c72b5edfb9561a981959b0e7c62d8ab9ef6c
+* port_machine: 146-193-182-187.edr.inesc.pt
+* port_time: 2023-11-08-11:42

config.json

@@ -0,0 +1,44 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 65000,
+  "decoder_vocab_size": 65001,
+  "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,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65001
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 65000,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 65000,
+  "transformers_version": "4.36.0.dev0"
+}

metadata.json

@@ -0,0 +1 @@
+{"hf_name": "eng-fra", "source_languages": "en", "target_languages": "fr", "opus_readme_url": "https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fra/opus-2021-02-22.zip/README.md", "original_repo": "Tatoeba-Challenge", "tags": ["translation"], "languages": ["en", "fr"], "src_constituents": ["eng"], "tgt_constituents": ["fra"], "src_multilingual": false, "tgt_multilingual": false, "helsinki_git_sha": "6faf2dab0b7b01a0e08a114dbacbb7deac54988d", "transformers_git_sha": "e9a6c72b5edfb9561a981959b0e7c62d8ab9ef6c", "port_machine": "146-193-182-187.edr.inesc.pt", "port_time": "2023-11-08-11:42"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:182db8a30b5b720e07e23248a24055599e001ddc800c200d7ab77bf61c951700
+size 221610115

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "fra",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}