upstream-archive snapshot of Helsinki-NLP/opus-mt-afa-afa (ADR-039 Phase D)

.gitattributes

@@ -1,35 +1,11 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt 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
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz 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
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl 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
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

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

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-afa-afa",
+  "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,
+  "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": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 33714
+}

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": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d19bb6c91793af99c13e563a628966b142d4066034ceaa709b6f6420d337e3c
+size 245764168

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191fc6c0ae01c8044b66544b34f00c3690d052af746cda8f07f4886f98d4df32
+size 842154

special_tokens_map.json

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

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1c1a7f37a9362214e7f93173e3d8e770cc7a2cf0375e5f92fcd2ef19db2b65
+size 842006

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
+    },
+    "33713": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "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>"
+}