Initial commit

.gitattributes

@@ -26,3 +26,4 @@ saved_model/**/* 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
+*.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,165 @@
+---
+language:
+- en
+- lt
+
+tags:
+- translation
+
+license: cc-by-4.0
+model-index:
+- name: opus-mt-tc-big-en-lt
+  results:
+  - task:
+      name: Translation eng-lit
+      type: translation
+      args: eng-lit
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: eng lit devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 28.0
+  - task:
+      name: Translation eng-lit
+      type: translation
+      args: eng-lit
+    dataset:
+      name: newsdev2019
+      type: newsdev2019
+      args: eng-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 26.6
+  - task:
+      name: Translation eng-lit
+      type: translation
+      args: eng-lit
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: eng-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 39.5
+  - task:
+      name: Translation eng-lit
+      type: translation
+      args: eng-lit
+    dataset:
+      name: newstest2019
+      type: wmt-2019-news
+      args: eng-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 17.5
+---
+# opus-mt-tc-big-en-lt
+
+Neural machine translation model for translating from English (en) to Lithuanian (lt).
+
+This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
+
+* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
+
+```
+@inproceedings{tiedemann-thottingal-2020-opus,
+    title = "{OPUS}-{MT} {--} Building open translation services for the World",
+    author = {Tiedemann, J{\"o}rg  and Thottingal, Santhosh},
+    booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
+    month = nov,
+    year = "2020",
+    address = "Lisboa, Portugal",
+    publisher = "European Association for Machine Translation",
+    url = "https://aclanthology.org/2020.eamt-1.61",
+    pages = "479--480",
+}
+
+@inproceedings{tiedemann-2020-tatoeba,
+    title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
+    author = {Tiedemann, J{\"o}rg},
+    booktitle = "Proceedings of the Fifth Conference on Machine Translation",
+    month = nov,
+    year = "2020",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2020.wmt-1.139",
+    pages = "1174--1182",
+}
+```
+
+## Model info
+
+* Release: 2022-02-25
+* source language(s): eng
+* target language(s): lit
+* model: transformer-big
+* data: opusTCv20210807+bt ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
+* tokenization: SentencePiece (spm32k,spm32k)
+* original model: [opusTCv20210807+bt_transformer-big_2022-02-25.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-lit/opusTCv20210807+bt_transformer-big_2022-02-25.zip)
+* more information released models: [OPUS-MT eng-lit README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-lit/README.md)
+
+## Usage
+
+A short example code:
+
+```python
+from transformers import MarianMTModel, MarianTokenizer
+
+src_text = [
+    "A cat was sitting on the chair.",
+    "Yukiko likes potatoes."
+]
+
+model_name = "pytorch-models/opus-mt-tc-big-en-lt"
+tokenizer = MarianTokenizer.from_pretrained(model_name)
+model = MarianMTModel.from_pretrained(model_name)
+translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
+
+for t in translated:
+    print( tokenizer.decode(t, skip_special_tokens=True) )
+
+# expected output:
+#     Katė sėdėjo ant kėdės.
+#     Jukiko mėgsta bulves.
+```
+
+You can also use OPUS-MT models with the transformers pipelines, for example:
+
+```python
+from transformers import pipeline
+pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-en-lt")
+print(pipe("A cat was sitting on the chair."))
+
+# expected output: Katė sėdėjo ant kėdės.
+```
+
+## Benchmarks
+
+* test set translations: [opusTCv20210807+bt_transformer-big_2022-02-25.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-lit/opusTCv20210807+bt_transformer-big_2022-02-25.test.txt)
+* test set scores: [opusTCv20210807+bt_transformer-big_2022-02-25.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-lit/opusTCv20210807+bt_transformer-big_2022-02-25.eval.txt)
+* benchmark results: [benchmark_results.txt](benchmark_results.txt)
+* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
+
+| langpair | testset | chr-F | BLEU  | #sent | #words |
+|----------|---------|-------|-------|-------|--------|
+| eng-lit | tatoeba-test-v2021-08-07 | 0.67434 | 39.5 | 2528 | 14942 |
+| eng-lit | flores101-devtest | 0.59593 | 28.0 | 1012 | 20695 |
+| eng-lit | newsdev2019 | 0.58444 | 26.6 | 2000 | 39627 |
+| eng-lit | newstest2019 | 0.51559 | 17.5 | 998 | 19711 |
+
+## Acknowledgements
+
+The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
+
+## Model conversion info
+
+* transformers version: 4.16.2
+* OPUS-MT git hash: 3405783
+* port time: Wed Apr 13 17:42:39 EEST 2022
+* port machine: LM0-400-22516.local

benchmark_results.txt

@@ -0,0 +1,7 @@
+eng-lit	flores101-dev	0.58441	26.5	997	20018
+eng-lit	flores101-devtest	0.59593	28.0	1012	20695
+eng-lit	newsdev2019	0.58444	26.6	2000	39627
+eng-lit	newstest2019	0.51559	17.5	998	19711
+eng-lit	tatoeba-test-v2020-07-28	0.67475	39.5	2500	14798
+eng-lit	tatoeba-test-v2021-03-30	0.67445	39.5	5003	29598
+eng-lit	tatoeba-test-v2021-08-07	0.67434	39.5	2528	14942

benchmark_translations.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef0fb7e466c9ee1ff2b5a495acd402ed7a5dcd288aef865dba427fde7dbe248
+size 1082504

config.json

@@ -0,0 +1,45 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      58576
+    ]
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 58576,
+  "decoder_vocab_size": 58577,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 44847,
+  "forced_eos_token_id": 44847,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 512,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 58576,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.18.0.dev0",
+  "use_cache": true,
+  "vocab_size": 58577
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c845392a4e8420335eb1a5f732a5696cc0e94c4f969607183b5a9cdcad09b3
+size 592854979

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c494c9df0fb537038a2f1fbd7794dd83e859745dae7a9b512c2263338d86177
+size 801213

special_tokens_map.json

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

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e652327bda51d3169693b50844168ff1f2d34d462ff9e3450bd23ed66a2f17
+size 836803

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "en", "target_lang": "lt", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "name_or_path": "marian-models/opusTCv20210807+bt_transformer-big_2022-02-25/en-lt", "tokenizer_class": "MarianTokenizer"}