Add files using upload-large-folder tool

Helsinki-NLP-opus-mt-en-luo/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-luo/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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
+    },
+    "52235": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "luo",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-lus/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-lus
+
+* source languages: en
+* target languages: lus
+*  OPUS readme: [en-lus](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-lus/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-01-08.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-lus/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-lus/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-lus/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.en.lus 	| 36.8 	| 0.581 |
+

Helsinki-NLP-opus-mt-en-lus/config.json

@@ -0,0 +1,56 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 49566,
+  "decoder_vocab_size": 49567,
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 49566,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 49567
+}

Helsinki-NLP-opus-mt-en-lus/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      49566
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 49566,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 49566,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-lus/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-lus/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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
+    },
+    "49566": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "lus",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-map/README.md

@@ -0,0 +1,127 @@
+---
+language: 
+- en
+- map
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### eng-map
+
+* source group: English 
+* target group: Austronesian languages 
+*  OPUS readme: [eng-map](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-map/README.md)
+
+*  model: transformer
+* source language(s): eng
+* target language(s): akl_Latn ceb cha dtp fij gil haw hil iba ilo ind jav jav_Java lkt mad mah max_Latn min mlg mri nau niu pag pau rap smo sun tah tet tmw_Latn ton tvl war zlm_Latn zsm_Latn
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
+* download original weights: [opus-2020-07-27.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-map/opus-2020-07-27.zip)
+* test set translations: [opus-2020-07-27.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-map/opus-2020-07-27.test.txt)
+* test set scores: [opus-2020-07-27.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-map/opus-2020-07-27.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.eng-akl.eng.akl 	| 2.2 	| 0.103 |
+| Tatoeba-test.eng-ceb.eng.ceb 	| 10.7 	| 0.425 |
+| Tatoeba-test.eng-cha.eng.cha 	| 3.2 	| 0.201 |
+| Tatoeba-test.eng-dtp.eng.dtp 	| 0.5 	| 0.120 |
+| Tatoeba-test.eng-fij.eng.fij 	| 26.8 	| 0.453 |
+| Tatoeba-test.eng-gil.eng.gil 	| 59.3 	| 0.762 |
+| Tatoeba-test.eng-haw.eng.haw 	| 1.0 	| 0.116 |
+| Tatoeba-test.eng-hil.eng.hil 	| 19.0 	| 0.517 |
+| Tatoeba-test.eng-iba.eng.iba 	| 15.5 	| 0.400 |
+| Tatoeba-test.eng-ilo.eng.ilo 	| 33.6 	| 0.591 |
+| Tatoeba-test.eng-jav.eng.jav 	| 7.8 	| 0.301 |
+| Tatoeba-test.eng-lkt.eng.lkt 	| 1.0 	| 0.064 |
+| Tatoeba-test.eng-mad.eng.mad 	| 1.1 	| 0.142 |
+| Tatoeba-test.eng-mah.eng.mah 	| 9.1 	| 0.374 |
+| Tatoeba-test.eng-mlg.eng.mlg 	| 35.4 	| 0.526 |
+| Tatoeba-test.eng-mri.eng.mri 	| 7.6 	| 0.309 |
+| Tatoeba-test.eng-msa.eng.msa 	| 31.1 	| 0.565 |
+| Tatoeba-test.eng.multi 	| 17.6 	| 0.411 |
+| Tatoeba-test.eng-nau.eng.nau 	| 1.4 	| 0.098 |
+| Tatoeba-test.eng-niu.eng.niu 	| 40.1 	| 0.560 |
+| Tatoeba-test.eng-pag.eng.pag 	| 16.8 	| 0.526 |
+| Tatoeba-test.eng-pau.eng.pau 	| 1.9 	| 0.139 |
+| Tatoeba-test.eng-rap.eng.rap 	| 2.7 	| 0.090 |
+| Tatoeba-test.eng-smo.eng.smo 	| 24.9 	| 0.453 |
+| Tatoeba-test.eng-sun.eng.sun 	| 33.2 	| 0.439 |
+| Tatoeba-test.eng-tah.eng.tah 	| 12.5 	| 0.278 |
+| Tatoeba-test.eng-tet.eng.tet 	| 1.6 	| 0.140 |
+| Tatoeba-test.eng-ton.eng.ton 	| 25.8 	| 0.530 |
+| Tatoeba-test.eng-tvl.eng.tvl 	| 31.1 	| 0.523 |
+| Tatoeba-test.eng-war.eng.war 	| 12.8 	| 0.436 |
+
+
+### System Info: 
+- hf_name: eng-map
+
+- source_languages: eng
+
+- target_languages: map
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-map/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['en', 'map']
+
+- src_constituents: {'eng'}
+
+- tgt_constituents: set()
+
+- src_multilingual: False
+
+- tgt_multilingual: True
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-map/opus-2020-07-27.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-map/opus-2020-07-27.test.txt
+
+- src_alpha3: eng
+
+- tgt_alpha3: map
+
+- short_pair: en-map
+
+- chrF2_score: 0.41100000000000003
+
+- bleu: 17.6
+
+- brevity_penalty: 1.0
+
+- ref_len: 66963.0
+
+- src_name: English
+
+- tgt_name: Austronesian languages
+
+- train_date: 2020-07-27
+
+- src_alpha2: en
+
+- tgt_alpha2: map
+
+- prefer_old: False
+
+- long_pair: eng-map
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-en-map/config.json

@@ -0,0 +1,56 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 60087,
+  "decoder_vocab_size": 60088,
+  "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": 60088,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 60087,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 60088
+}

Helsinki-NLP-opus-mt-en-map/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      60087
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 60087,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 60087,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-map/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-map/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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
+    },
+    "60087": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "map",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-mfe/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-mfe
+
+* source languages: en
+* target languages: mfe
+*  OPUS readme: [en-mfe](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-mfe/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-01-08.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-mfe/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mfe/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mfe/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.en.mfe 	| 32.1 	| 0.509 |
+

Helsinki-NLP-opus-mt-en-mfe/config.json

@@ -0,0 +1,56 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 48882,
+  "decoder_vocab_size": 48883,
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 48882,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 48883
+}

Helsinki-NLP-opus-mt-en-mfe/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      48882
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 48882,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 48882,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-mfe/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-mfe/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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
+    },
+    "48882": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "mfe",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-mg/README.md

@@ -0,0 +1,26 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-mg
+
+* source languages: en
+* target languages: mg
+*  OPUS readme: [en-mg](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-mg/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-01-08.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-mg/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mg/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mg/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| GlobalVoices.en.mg 	| 22.3 	| 0.565 |
+| Tatoeba.en.mg 	| 35.5 	| 0.548 |
+

Helsinki-NLP-opus-mt-en-mg/config.json

@@ -0,0 +1,56 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 54687,
+  "decoder_vocab_size": 54688,
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 54687,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 54688
+}

Helsinki-NLP-opus-mt-en-mg/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      54687
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 54687,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 54687,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-mg/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-mg/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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
+    },
+    "54687": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "mg",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-mh/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-mh
+
+* source languages: en
+* target languages: mh
+*  OPUS readme: [en-mh](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-mh/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-01-08.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-mh/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mh/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mh/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.en.mh 	| 29.7 	| 0.479 |
+

Helsinki-NLP-opus-mt-en-mh/config.json

@@ -0,0 +1,56 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 49656,
+  "decoder_vocab_size": 49657,
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 49656,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 49657
+}

Helsinki-NLP-opus-mt-en-mh/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      49656
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 49656,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 49656,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-mh/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-mh/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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
+    },
+    "49656": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "mh",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-mk/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-mk
+
+* source languages: en
+* target languages: mk
+*  OPUS readme: [en-mk](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-mk/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2019-12-18.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-mk/opus-2019-12-18.zip)
+* test set translations: [opus-2019-12-18.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mk/opus-2019-12-18.test.txt)
+* test set scores: [opus-2019-12-18.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mk/opus-2019-12-18.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba.en.mk 	| 52.1 	| 0.683 |
+

Helsinki-NLP-opus-mt-en-mk/config.json

@@ -0,0 +1,56 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 61945,
+  "decoder_vocab_size": 61946,
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 61945,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 61946
+}

Helsinki-NLP-opus-mt-en-mk/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      61945
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 61945,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 61945,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-mk/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-mk/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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
+    },
+    "61945": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "mk",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-mkh/README.md

@@ -0,0 +1,104 @@
+---
+language: 
+- en
+- vi
+- km
+- mkh
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### eng-mkh
+
+* source group: English 
+* target group: Mon-Khmer languages 
+*  OPUS readme: [eng-mkh](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-mkh/README.md)
+
+*  model: transformer
+* source language(s): eng
+* target language(s): kha khm khm_Latn mnw vie vie_Hani
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
+* download original weights: [opus-2020-07-27.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.zip)
+* test set translations: [opus-2020-07-27.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.test.txt)
+* test set scores: [opus-2020-07-27.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.eng-kha.eng.kha 	| 0.1 	| 0.015 |
+| Tatoeba-test.eng-khm.eng.khm 	| 0.2 	| 0.226 |
+| Tatoeba-test.eng-mnw.eng.mnw 	| 0.7 	| 0.003 |
+| Tatoeba-test.eng.multi 	| 16.5 	| 0.330 |
+| Tatoeba-test.eng-vie.eng.vie 	| 33.7 	| 0.513 |
+
+
+### System Info: 
+- hf_name: eng-mkh
+
+- source_languages: eng
+
+- target_languages: mkh
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-mkh/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['en', 'vi', 'km', 'mkh']
+
+- src_constituents: {'eng'}
+
+- tgt_constituents: {'vie_Hani', 'mnw', 'vie', 'kha', 'khm_Latn', 'khm'}
+
+- src_multilingual: False
+
+- tgt_multilingual: True
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.test.txt
+
+- src_alpha3: eng
+
+- tgt_alpha3: mkh
+
+- short_pair: en-mkh
+
+- chrF2_score: 0.33
+
+- bleu: 16.5
+
+- brevity_penalty: 1.0
+
+- ref_len: 34734.0
+
+- src_name: English
+
+- tgt_name: Mon-Khmer languages
+
+- train_date: 2020-07-27
+
+- src_alpha2: en
+
+- tgt_alpha2: mkh
+
+- prefer_old: False
+
+- long_pair: eng-mkh
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-en-mkh/config.json

@@ -0,0 +1,56 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 56074,
+  "decoder_vocab_size": 56075,
+  "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": 56075,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 56074,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 56075
+}

Helsinki-NLP-opus-mt-en-mkh/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      56074
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 56074,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 56074,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-mkh/special_tokens_map.json

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