Add files using upload-large-folder tool

Helsinki-NLP-opus-mt-af-fr/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-af-fr
+
+* source languages: af
+* target languages: fr
+*  OPUS readme: [af-fr](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/af-fr/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/af-fr/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/af-fr/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/af-fr/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.af.fr 	| 35.3 	| 0.543 |
+

Helsinki-NLP-opus-mt-af-fr/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": 59421,
+  "decoder_vocab_size": 59422,
+  "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": 59421,
+  "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": 59422
+}

Helsinki-NLP-opus-mt-af-fr/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      59421
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59421,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59421,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-af-fr/special_tokens_map.json

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

Helsinki-NLP-opus-mt-af-fr/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
+    },
+    "59421": {
+      "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": "af",
+  "sp_model_kwargs": {},
+  "target_lang": "fr",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-af-nl/README.md

@@ -0,0 +1,97 @@
+---
+language: 
+- af
+- nl
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### afr-nld
+
+* source group: Afrikaans 
+* target group: Dutch 
+*  OPUS readme: [afr-nld](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afr-nld/README.md)
+
+*  model: transformer-align
+* source language(s): afr
+* target language(s): nld
+* model: transformer-align
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-06-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-nld/opus-2020-06-17.zip)
+* test set translations: [opus-2020-06-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-nld/opus-2020-06-17.test.txt)
+* test set scores: [opus-2020-06-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-nld/opus-2020-06-17.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.afr.nld 	| 55.2 	| 0.715 |
+
+
+### System Info: 
+- hf_name: afr-nld
+
+- source_languages: afr
+
+- target_languages: nld
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afr-nld/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['af', 'nl']
+
+- src_constituents: {'afr'}
+
+- tgt_constituents: {'nld'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/afr-nld/opus-2020-06-17.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/afr-nld/opus-2020-06-17.test.txt
+
+- src_alpha3: afr
+
+- tgt_alpha3: nld
+
+- short_pair: af-nl
+
+- chrF2_score: 0.715
+
+- bleu: 55.2
+
+- brevity_penalty: 0.995
+
+- ref_len: 6710.0
+
+- src_name: Afrikaans
+
+- tgt_name: Dutch
+
+- train_date: 2020-06-17
+
+- src_alpha2: af
+
+- tgt_alpha2: nl
+
+- prefer_old: False
+
+- long_pair: afr-nld
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-af-nl/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": 53246,
+  "decoder_vocab_size": 53247,
+  "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": 53247,
+  "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": 53246,
+  "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": 53247
+}

Helsinki-NLP-opus-mt-af-nl/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      53246
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 53246,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 53246,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-af-nl/special_tokens_map.json

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

Helsinki-NLP-opus-mt-af-nl/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
+    },
+    "53246": {
+      "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": "afr",
+  "sp_model_kwargs": {},
+  "target_lang": "nld",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-af-ru/README.md

@@ -0,0 +1,97 @@
+---
+language: 
+- af
+- ru
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### afr-rus
+
+* source group: Afrikaans 
+* target group: Russian 
+*  OPUS readme: [afr-rus](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afr-rus/README.md)
+
+*  model: transformer-align
+* source language(s): afr
+* target language(s): rus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-06-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-06-17.zip)
+* test set translations: [opus-2020-06-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-06-17.test.txt)
+* test set scores: [opus-2020-06-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-06-17.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.afr.rus 	| 38.2 	| 0.580 |
+
+
+### System Info: 
+- hf_name: afr-rus
+
+- source_languages: afr
+
+- target_languages: rus
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afr-rus/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['af', 'ru']
+
+- src_constituents: {'afr'}
+
+- tgt_constituents: {'rus'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-06-17.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-06-17.test.txt
+
+- src_alpha3: afr
+
+- tgt_alpha3: rus
+
+- short_pair: af-ru
+
+- chrF2_score: 0.58
+
+- bleu: 38.2
+
+- brevity_penalty: 0.992
+
+- ref_len: 1213.0
+
+- src_name: Afrikaans
+
+- tgt_name: Russian
+
+- train_date: 2020-06-17
+
+- src_alpha2: af
+
+- tgt_alpha2: ru
+
+- prefer_old: False
+
+- long_pair: afr-rus
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-af-ru/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": 62841,
+  "decoder_vocab_size": 62842,
+  "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": 62842,
+  "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": 62841,
+  "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": 62842
+}

Helsinki-NLP-opus-mt-af-ru/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      62841
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62841,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62841,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-af-ru/special_tokens_map.json

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

Helsinki-NLP-opus-mt-af-ru/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
+    },
+    "62841": {
+      "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": "afr",
+  "sp_model_kwargs": {},
+  "target_lang": "rus",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-af-sv/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-af-sv
+
+* source languages: af
+* target languages: sv
+*  OPUS readme: [af-sv](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/af-sv/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/af-sv/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/af-sv/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/af-sv/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.af.sv 	| 40.4 	| 0.599 |
+

Helsinki-NLP-opus-mt-af-sv/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": 58462,
+  "decoder_vocab_size": 58463,
+  "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": 58462,
+  "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": 58463
+}

Helsinki-NLP-opus-mt-af-sv/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      58462
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 58462,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 58462,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-af-sv/special_tokens_map.json

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

Helsinki-NLP-opus-mt-af-sv/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
+    },
+    "58462": {
+      "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": "af",
+  "sp_model_kwargs": {},
+  "target_lang": "sv",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-afa-afa/README.md

@@ -0,0 +1,118 @@
+---
+language: 
+- so
+- ti
+- am
+- he
+- mt
+- ar
+- afa
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### afa-afa
+
+* source group: Afro-Asiatic languages 
+* target group: Afro-Asiatic languages 
+*  OPUS readme: [afa-afa](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afa-afa/README.md)
+
+*  model: transformer
+* source language(s): apc ara arq arz heb kab mlt shy_Latn thv
+* target language(s): apc ara arq arz heb kab mlt shy_Latn thv
+* 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-2020-07-26.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-afa/opus-2020-07-26.zip)
+* test set translations: [opus-2020-07-26.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-afa/opus-2020-07-26.test.txt)
+* test set scores: [opus-2020-07-26.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-afa/opus-2020-07-26.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.ara-ara.ara.ara 	| 4.3 	| 0.148 |
+| Tatoeba-test.ara-heb.ara.heb 	| 31.9 	| 0.525 |
+| Tatoeba-test.ara-kab.ara.kab 	| 0.3 	| 0.120 |
+| Tatoeba-test.ara-mlt.ara.mlt 	| 14.0 	| 0.428 |
+| Tatoeba-test.ara-shy.ara.shy 	| 1.3 	| 0.050 |
+| Tatoeba-test.heb-ara.heb.ara 	| 17.0 	| 0.464 |
+| Tatoeba-test.heb-kab.heb.kab 	| 1.9 	| 0.104 |
+| Tatoeba-test.kab-ara.kab.ara 	| 0.3 	| 0.044 |
+| Tatoeba-test.kab-heb.kab.heb 	| 5.1 	| 0.099 |
+| Tatoeba-test.kab-shy.kab.shy 	| 2.2 	| 0.009 |
+| Tatoeba-test.kab-tmh.kab.tmh 	| 10.7 	| 0.007 |
+| Tatoeba-test.mlt-ara.mlt.ara 	| 29.1 	| 0.498 |
+| Tatoeba-test.multi.multi 	| 20.8 	| 0.434 |
+| Tatoeba-test.shy-ara.shy.ara 	| 1.2 	| 0.053 |
+| Tatoeba-test.shy-kab.shy.kab 	| 2.0 	| 0.134 |
+| Tatoeba-test.tmh-kab.tmh.kab 	| 0.0 	| 0.047 |
+
+
+### System Info: 
+- hf_name: afa-afa
+
+- source_languages: afa
+
+- target_languages: afa
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afa-afa/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['so', 'ti', 'am', 'he', 'mt', 'ar', 'afa']
+
+- src_constituents: {'som', 'rif_Latn', 'tir', 'kab', 'arq', 'afb', 'amh', 'arz', 'heb', 'shy_Latn', 'apc', 'mlt', 'thv', 'ara', 'hau_Latn', 'acm', 'ary'}
+
+- tgt_constituents: {'som', 'rif_Latn', 'tir', 'kab', 'arq', 'afb', 'amh', 'arz', 'heb', 'shy_Latn', 'apc', 'mlt', 'thv', 'ara', 'hau_Latn', 'acm', 'ary'}
+
+- src_multilingual: True
+
+- tgt_multilingual: True
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/afa-afa/opus-2020-07-26.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/afa-afa/opus-2020-07-26.test.txt
+
+- src_alpha3: afa
+
+- tgt_alpha3: afa
+
+- short_pair: afa-afa
+
+- chrF2_score: 0.434
+
+- bleu: 20.8
+
+- brevity_penalty: 1.0
+
+- ref_len: 15215.0
+
+- src_name: Afro-Asiatic languages
+
+- tgt_name: Afro-Asiatic languages
+
+- train_date: 2020-07-26
+
+- src_alpha2: afa
+
+- tgt_alpha2: afa
+
+- prefer_old: False
+
+- long_pair: afa-afa
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-afa-afa/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": 33713,
+  "decoder_vocab_size": 33714,
+  "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": 33714,
+  "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": 33713,
+  "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": 33714
+}

Helsinki-NLP-opus-mt-afa-afa/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      33713
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 33713,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 33713,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-afa-afa/special_tokens_map.json

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

Helsinki-NLP-opus-mt-afa-afa/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
+    },
+    "33713": {
+      "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": "afa",
+  "sp_model_kwargs": {},
+  "target_lang": "afa",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

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

@@ -0,0 +1,113 @@
+---
+language: 
+- so
+- ti
+- am
+- he
+- mt
+- ar
+- afa
+- en
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### afa-eng
+
+* source group: Afro-Asiatic languages 
+* target group: English 
+*  OPUS readme: [afa-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afa-eng/README.md)
+
+*  model: transformer
+* source language(s): acm afb amh apc ara arq ary arz hau_Latn heb kab mlt rif_Latn shy_Latn som tir
+* target language(s): eng
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus2m-2020-07-31.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-eng/opus2m-2020-07-31.zip)
+* test set translations: [opus2m-2020-07-31.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-eng/opus2m-2020-07-31.test.txt)
+* test set scores: [opus2m-2020-07-31.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-eng/opus2m-2020-07-31.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.amh-eng.amh.eng 	| 35.9 	| 0.550 |
+| Tatoeba-test.ara-eng.ara.eng 	| 36.6 	| 0.543 |
+| Tatoeba-test.hau-eng.hau.eng 	| 11.9 	| 0.327 |
+| Tatoeba-test.heb-eng.heb.eng 	| 42.7 	| 0.591 |
+| Tatoeba-test.kab-eng.kab.eng 	| 4.3 	| 0.213 |
+| Tatoeba-test.mlt-eng.mlt.eng 	| 44.3 	| 0.618 |
+| Tatoeba-test.multi.eng 	| 27.1 	| 0.464 |
+| Tatoeba-test.rif-eng.rif.eng 	| 3.5 	| 0.141 |
+| Tatoeba-test.shy-eng.shy.eng 	| 0.6 	| 0.125 |
+| Tatoeba-test.som-eng.som.eng 	| 23.6 	| 0.472 |
+| Tatoeba-test.tir-eng.tir.eng 	| 13.1 	| 0.328 |
+
+
+### System Info: 
+- hf_name: afa-eng
+
+- source_languages: afa
+
+- target_languages: eng
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afa-eng/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['so', 'ti', 'am', 'he', 'mt', 'ar', 'afa', 'en']
+
+- src_constituents: {'som', 'rif_Latn', 'tir', 'kab', 'arq', 'afb', 'amh', 'arz', 'heb', 'shy_Latn', 'apc', 'mlt', 'thv', 'ara', 'hau_Latn', 'acm', 'ary'}
+
+- tgt_constituents: {'eng'}
+
+- src_multilingual: True
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/afa-eng/opus2m-2020-07-31.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/afa-eng/opus2m-2020-07-31.test.txt
+
+- src_alpha3: afa
+
+- tgt_alpha3: eng
+
+- short_pair: afa-en
+
+- chrF2_score: 0.46399999999999997
+
+- bleu: 27.1
+
+- brevity_penalty: 1.0
+
+- ref_len: 69373.0
+
+- src_name: Afro-Asiatic languages
+
+- tgt_name: English
+
+- train_date: 2020-07-31
+
+- src_alpha2: afa
+
+- tgt_alpha2: en
+
+- prefer_old: False
+
+- long_pair: afa-eng
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-afa-en/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": 61179,
+  "decoder_vocab_size": 61180,
+  "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": 61180,
+  "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": 61179,
+  "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": 61180
+}

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

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      61179
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 61179,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 61179,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

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

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

Helsinki-NLP-opus-mt-afa-en/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
+    },
+    "61179": {
+      "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": "afa",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

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

@@ -0,0 +1,129 @@
+---
+language: 
+- sn
+- rw
+- wo
+- ig
+- sg
+- ee
+- zu
+- lg
+- ts
+- ln
+- ny
+- yo
+- rn
+- xh
+- alv
+- en
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### alv-eng
+
+* source group: Atlantic-Congo languages 
+* target group: English 
+*  OPUS readme: [alv-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/alv-eng/README.md)
+
+*  model: transformer
+* source language(s): ewe fuc fuv ibo kin lin lug nya run sag sna swh toi_Latn tso umb wol xho yor zul
+* target language(s): eng
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus2m-2020-07-31.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/alv-eng/opus2m-2020-07-31.zip)
+* test set translations: [opus2m-2020-07-31.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/alv-eng/opus2m-2020-07-31.test.txt)
+* test set scores: [opus2m-2020-07-31.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/alv-eng/opus2m-2020-07-31.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.ewe-eng.ewe.eng 	| 6.3 	| 0.328 |
+| Tatoeba-test.ful-eng.ful.eng 	| 0.4 	| 0.108 |
+| Tatoeba-test.ibo-eng.ibo.eng 	| 4.5 	| 0.196 |
+| Tatoeba-test.kin-eng.kin.eng 	| 30.7 	| 0.511 |
+| Tatoeba-test.lin-eng.lin.eng 	| 2.8 	| 0.213 |
+| Tatoeba-test.lug-eng.lug.eng 	| 3.4 	| 0.140 |
+| Tatoeba-test.multi.eng 	| 20.9 	| 0.376 |
+| Tatoeba-test.nya-eng.nya.eng 	| 38.7 	| 0.492 |
+| Tatoeba-test.run-eng.run.eng 	| 24.5 	| 0.417 |
+| Tatoeba-test.sag-eng.sag.eng 	| 5.5 	| 0.177 |
+| Tatoeba-test.sna-eng.sna.eng 	| 26.9 	| 0.412 |
+| Tatoeba-test.swa-eng.swa.eng 	| 4.9 	| 0.196 |
+| Tatoeba-test.toi-eng.toi.eng 	| 3.9 	| 0.147 |
+| Tatoeba-test.tso-eng.tso.eng 	| 76.7 	| 0.957 |
+| Tatoeba-test.umb-eng.umb.eng 	| 4.0 	| 0.195 |
+| Tatoeba-test.wol-eng.wol.eng 	| 3.7 	| 0.170 |
+| Tatoeba-test.xho-eng.xho.eng 	| 38.9 	| 0.556 |
+| Tatoeba-test.yor-eng.yor.eng 	| 25.1 	| 0.412 |
+| Tatoeba-test.zul-eng.zul.eng 	| 46.1 	| 0.623 |
+
+
+### System Info: 
+- hf_name: alv-eng
+
+- source_languages: alv
+
+- target_languages: eng
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/alv-eng/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['sn', 'rw', 'wo', 'ig', 'sg', 'ee', 'zu', 'lg', 'ts', 'ln', 'ny', 'yo', 'rn', 'xh', 'alv', 'en']
+
+- src_constituents: {'sna', 'kin', 'wol', 'ibo', 'swh', 'sag', 'ewe', 'zul', 'fuc', 'lug', 'tso', 'lin', 'nya', 'yor', 'run', 'xho', 'fuv', 'toi_Latn', 'umb'}
+
+- tgt_constituents: {'eng'}
+
+- src_multilingual: True
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/alv-eng/opus2m-2020-07-31.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/alv-eng/opus2m-2020-07-31.test.txt
+
+- src_alpha3: alv
+
+- tgt_alpha3: eng
+
+- short_pair: alv-en
+
+- chrF2_score: 0.376
+
+- bleu: 20.9
+
+- brevity_penalty: 1.0
+
+- ref_len: 15208.0
+
+- src_name: Atlantic-Congo languages
+
+- tgt_name: English
+
+- train_date: 2020-07-31
+
+- src_alpha2: alv
+
+- tgt_alpha2: en
+
+- prefer_old: False
+
+- long_pair: alv-eng
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-alv-en/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": 61548,
+  "decoder_vocab_size": 61549,
+  "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": 61549,
+  "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": 61548,
+  "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": 61549
+}

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

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      61548
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 61548,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 61548,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

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

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

Helsinki-NLP-opus-mt-alv-en/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
+    },
+    "61548": {
+      "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": "alv",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-am-sv/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-am-sv
+
+* source languages: am
+* target languages: sv
+*  OPUS readme: [am-sv](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/am-sv/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/am-sv/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/am-sv/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/am-sv/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.am.sv 	| 21.0 	| 0.377 |
+