Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+*.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,487 @@
+---
+library_name: transformers
+language:
+- bru
+- cmo
+- de
+- en
+- es
+- fr
+- hoc
+- jun
+- kha
+- km
+- kxm
+- mnw
+- ngt
+- pt
+- sat
+- vi
+- wbm
+
+tags:
+- translation
+- opus-mt-tc-bible
+
+license: apache-2.0
+model-index:
+- name: opus-mt-tc-bible-big-deu_eng_fra_por_spa-aav
+  results:
+  - task:
+      name: Translation deu-vie
+      type: translation
+      args: deu-vie
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: deu-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 34.0
+       - name: chr-F
+         type: chrf
+         value: 0.53671
+  - task:
+      name: Translation eng-vie
+      type: translation
+      args: eng-vie
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: eng-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 42.4
+       - name: chr-F
+         type: chrf
+         value: 0.59842
+  - task:
+      name: Translation fra-vie
+      type: translation
+      args: fra-vie
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: fra-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 34.6
+       - name: chr-F
+         type: chrf
+         value: 0.54101
+  - task:
+      name: Translation por-vie
+      type: translation
+      args: por-vie
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: por-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 36.1
+       - name: chr-F
+         type: chrf
+         value: 0.54970
+  - task:
+      name: Translation spa-vie
+      type: translation
+      args: spa-vie
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: spa-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 28.1
+       - name: chr-F
+         type: chrf
+         value: 0.50025
+  - task:
+      name: Translation deu-vie
+      type: translation
+      args: deu-vie
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: deu vie devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 33.8
+       - name: chr-F
+         type: chrf
+         value: 0.53381
+  - task:
+      name: Translation eng-vie
+      type: translation
+      args: eng-vie
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: eng vie devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 42.1
+       - name: chr-F
+         type: chrf
+         value: 0.59621
+  - task:
+      name: Translation por-vie
+      type: translation
+      args: por-vie
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: por vie devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 36.0
+       - name: chr-F
+         type: chrf
+         value: 0.54919
+  - task:
+      name: Translation spa-vie
+      type: translation
+      args: spa-vie
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: spa vie devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 27.8
+       - name: chr-F
+         type: chrf
+         value: 0.49921
+  - task:
+      name: Translation deu-vie
+      type: translation
+      args: deu-vie
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: deu-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 31.4
+       - name: chr-F
+         type: chrf
+         value: 0.52124
+  - task:
+      name: Translation fra-vie
+      type: translation
+      args: fra-vie
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: fra-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 31.8
+       - name: chr-F
+         type: chrf
+         value: 0.52044
+  - task:
+      name: Translation por-vie
+      type: translation
+      args: por-vie
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: por-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 33.3
+       - name: chr-F
+         type: chrf
+         value: 0.53060
+  - task:
+      name: Translation spa-vie
+      type: translation
+      args: spa-vie
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: spa-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 33.4
+       - name: chr-F
+         type: chrf
+         value: 0.53293
+  - task:
+      name: Translation deu-vie
+      type: translation
+      args: deu-vie
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: deu-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 25.6
+       - name: chr-F
+         type: chrf
+         value: 0.45795
+  - task:
+      name: Translation eng-vie
+      type: translation
+      args: eng-vie
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: eng-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 39.4
+       - name: chr-F
+         type: chrf
+         value: 0.56461
+  - task:
+      name: Translation fra-vie
+      type: translation
+      args: fra-vie
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: fra-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 35.2
+       - name: chr-F
+         type: chrf
+         value: 0.52806
+  - task:
+      name: Translation multi-multi
+      type: translation
+      args: multi-multi
+    dataset:
+      name: tatoeba-test-v2020-07-28-v2023-09-26
+      type: tatoeba_mt
+      args: multi-multi
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.9
+       - name: chr-F
+         type: chrf
+         value: 0.40649
+  - task:
+      name: Translation spa-vie
+      type: translation
+      args: spa-vie
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: spa-vie
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 34.2
+       - name: chr-F
+         type: chrf
+         value: 0.52131
+---
+# opus-mt-tc-bible-big-deu_eng_fra_por_spa-aav
+
+## Table of Contents
+- [Model Details](#model-details)
+- [Uses](#uses)
+- [Risks, Limitations and Biases](#risks-limitations-and-biases)
+- [How to Get Started With the Model](#how-to-get-started-with-the-model)
+- [Training](#training)
+- [Evaluation](#evaluation)
+- [Citation Information](#citation-information)
+- [Acknowledgements](#acknowledgements)
+
+## Model Details
+
+Neural machine translation model for translating from unknown (deu+eng+fra+por+spa) to Austro-Asiatic languages (aav).
+
+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).
+**Model Description:**
+- **Developed by:** Language Technology Research Group at the University of Helsinki
+- **Model Type:** Translation (transformer-big)
+- **Release**: 2024-05-29
+- **License:** Apache-2.0
+- **Language(s):**  
+  - Source Language(s): deu eng fra por spa
+  - Target Language(s): bru cmo hoc jun kha khm kxm mnw ngt sat vie wbm
+  - Valid Target Language Labels: >>aem<< >>alk<< >>aml<< >>asr<< >>bbh<< >>bdq<< >>bfw<< >>bgk<< >>bgl<< >>bix<< >>biy<< >>blr<< >>brb<< >>bru<< >>brv<< >>btq<< >>caq<< >>cbn<< >>cdz<< >>cma<< >>cmo<< >>cog<< >>crv<< >>crw<< >>cua<< >>cwg<< >>dnu<< >>ekl<< >>gaq<< >>gbj<< >>hal<< >>hld<< >>hnu<< >>hoc<< >>hoc_Wara<< >>hre<< >>huo<< >>irr<< >>jah<< >>jeh<< >>jhi<< >>jun<< >>juy<< >>kdt<< >>kfp<< >>kfq<< >>kha<< >>khf<< >>khm<< >>khr<< >>kjg<< >>kjm<< >>knq<< >>kns<< >>kpm<< >>krr<< >>krv<< >>ksz<< >>kta<< >>ktv<< >>kuf<< >>kxm<< >>kxy<< >>lbn<< >>lbo<< >>lcp<< >>lnh<< >>lwl<< >>lyg<< >>mef<< >>mhe<< >>mjx<< >>mlf<< >>mmj<< >>mml<< >>mng<< >>mnn<< >>mnq<< >>mnw<< >>moo<< >>mqt<< >>mra<< >>mtq<< >>mzt<< >>ncb<< >>ncq<< >>nev<< >>ngt<< >>ngt_Latn<< >>nik<< >>nuo<< >>nyl<< >>omx<< >>oog<< >>oyb<< >>pac<< >>pbv<< >>pcb<< >>pce<< >>pcj<< >>phg<< >>pkt<< >>pll<< >>ply<< >>pnx<< >>prk<< >>prt<< >>puo<< >>rbb<< >>ren<< >>ril<< >>rka<< >>rmx<< >>sat<< >>sat_Latn<< >>sbo<< >>scb<< >>scq<< >>sct<< >>sea<< >>sed<< >>sii<< >>smu<< >>spu<< >>sqq<< >>srb<< >>ssm<< >>sss<< >>stg<< >>sti<< >>stt<< >>stu<< >>syo<< >>sza<< >>szc<< >>tdf<< >>tdr<< >>tea<< >>tef<< >>thm<< >>tkz<< >>tlq<< >>tmo<< >>tnz<< >>tou<< >>tpu<< >>trd<< >>tth<< >>tto<< >>tyh<< >>unr<< >>uuu<< >>vie<< >>vwa<< >>wbm<< >>xao<< >>xkk<< >>xnh<< >>xxx<< >>yin<< >>zng<<
+- **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-aav/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip)
+- **Resources for more information:**
+  -  [OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/deu%2Beng%2Bfra%2Bpor%2Bspa-aav/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-29)
+  - [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
+  - [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
+  - [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/)
+  - [HPLT bilingual data v1 (as part of the Tatoeba Translation Challenge dataset)](https://hplt-project.org/datasets/v1)
+  - [A massively parallel Bible corpus](https://aclanthology.org/L14-1215/)
+
+This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>bru<<`
+
+## Uses
+
+This model can be used for translation and text-to-text generation.
+
+## Risks, Limitations and Biases
+
+**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
+
+Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
+
+## How to Get Started With the Model
+
+A short example code:
+
+```python
+from transformers import MarianMTModel, MarianTokenizer
+
+src_text = [
+    ">>khm<< Der Junge wirft einen Stein.",
+    ">>vie<< ¿Y tú?"
+]
+
+model_name = "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-aav"
+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:
+#     ក្មេងប្រុស នោះ យក ដុំ ថ្ម គប់ ។
+#     Còn anh thì sao?
+```
+
+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-bible-big-deu_eng_fra_por_spa-aav")
+print(pipe(">>khm<< Der Junge wirft einen Stein."))
+
+# expected output: ក្មេងប្រុស នោះ យក ដុំ ថ្ម គប់ ។
+```
+
+## Training
+
+- **Data**: opusTCv20230926max50+bt+jhubc ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
+- **Pre-processing**: SentencePiece (spm32k,spm32k)
+- **Model Type:**  transformer-big
+- **Original MarianNMT Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-aav/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip)
+- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
+
+## Evaluation
+
+* [Model scores at the OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/deu%2Beng%2Bfra%2Bpor%2Bspa-aav/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-29)
+* test set translations: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-aav/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt)
+* test set scores: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-aav/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.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 |
+|----------|---------|-------|-------|-------|--------|
+| deu-vie | tatoeba-test-v2021-08-07 | 0.45795 | 25.6 | 400 | 3768 |
+| eng-hoc | tatoeba-test-v2021-08-07 | 6.438 | 0.2 | 660 | 2591 |
+| eng-kha | tatoeba-test-v2021-08-07 | 5.741 | 0.0 | 1314 | 9269 |
+| eng-vie | tatoeba-test-v2021-08-07 | 0.56461 | 39.4 | 2500 | 24427 |
+| fra-vie | tatoeba-test-v2021-08-07 | 0.52806 | 35.2 | 1299 | 13219 |
+| spa-vie | tatoeba-test-v2021-08-07 | 0.52131 | 34.2 | 594 | 4740 |
+| deu-vie | flores101-devtest | 0.53381 | 33.8 | 1012 | 33331 |
+| eng-khm | flores101-devtest | 0.42302 | 1.3 | 1012 | 7006 |
+| eng-vie | flores101-devtest | 0.59621 | 42.1 | 1012 | 33331 |
+| fra-khm | flores101-devtest | 0.40042 | 2.2 | 1012 | 7006 |
+| por-khm | flores101-devtest | 0.40585 | 2.1 | 1012 | 7006 |
+| por-vie | flores101-devtest | 0.54919 | 36.0 | 1012 | 33331 |
+| spa-vie | flores101-devtest | 0.49921 | 27.8 | 1012 | 33331 |
+| deu-vie | flores200-devtest | 0.53671 | 34.0 | 1012 | 33331 |
+| eng-khm | flores200-devtest | 0.42148 | 1.3 | 1012 | 7006 |
+| eng-vie | flores200-devtest | 0.59842 | 42.4 | 1012 | 33331 |
+| fra-vie | flores200-devtest | 0.54101 | 34.6 | 1012 | 33331 |
+| por-khm | flores200-devtest | 0.40832 | 1.9 | 1012 | 7006 |
+| por-vie | flores200-devtest | 0.54970 | 36.1 | 1012 | 33331 |
+| spa-vie | flores200-devtest | 0.50025 | 28.1 | 1012 | 33331 |
+| deu-khm | ntrex128 | 0.44903 | 3.5 | 1997 | 15866 |
+| deu-vie | ntrex128 | 0.52124 | 31.4 | 1997 | 64655 |
+| eng-khm | ntrex128 | 0.50494 | 1.6 | 1997 | 15866 |
+| eng-vie | ntrex128 | 3.831 | 0.0 | 1997 | 64655 |
+| fra-khm | ntrex128 | 0.43841 | 2.4 | 1997 | 15866 |
+| fra-vie | ntrex128 | 0.52044 | 31.8 | 1997 | 64655 |
+| por-khm | ntrex128 | 0.46655 | 2.5 | 1997 | 15866 |
+| por-vie | ntrex128 | 0.53060 | 33.3 | 1997 | 64655 |
+| spa-khm | ntrex128 | 0.46443 | 2.7 | 1997 | 15866 |
+| spa-vie | ntrex128 | 0.53293 | 33.4 | 1997 | 64655 |
+| eng-khm | tico19-test | 0.47806 | 2.5 | 2100 | 15810 |
+| fra-khm | tico19-test | 3.268 | 1.0 | 2100 | 15810 |
+| por-khm | tico19-test | 3.900 | 1.1 | 2100 | 15810 |
+| spa-khm | tico19-test | 3.784 | 1.0 | 2100 | 15810 |
+
+## Citation Information
+
+* Publications: [Democratizing neural machine translation with OPUS-MT](https://doi.org/10.1007/s10579-023-09704-w) and [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.)
+
+```bibtex
+@article{tiedemann2023democratizing,
+  title={Democratizing neural machine translation with {OPUS-MT}},
+  author={Tiedemann, J{\"o}rg and Aulamo, Mikko and Bakshandaeva, Daria and Boggia, Michele and Gr{\"o}nroos, Stig-Arne and Nieminen, Tommi and Raganato, Alessandro and Scherrer, Yves and Vazquez, Raul and Virpioja, Sami},
+  journal={Language Resources and Evaluation},
+  number={58},
+  pages={713--755},
+  year={2023},
+  publisher={Springer Nature},
+  issn={1574-0218},
+  doi={10.1007/s10579-023-09704-w}
+}
+
+@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",
+}
+```
+
+## Acknowledgements
+
+The work is supported by the [HPLT project](https://hplt-project.org/), funded by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101070350. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland, and the [EuroHPC supercomputer LUMI](https://www.lumi-supercomputer.eu/).
+
+## Model conversion info
+
+* transformers version: 4.45.1
+* OPUS-MT git hash: 0882077
+* port time: Tue Oct  8 00:06:48 EEST 2024
+* port machine: LM0-400-22516.local

benchmark_results.txt

@@ -0,0 +1,56 @@
+multi-multi	tatoeba-test-v2020-07-28-v2023-09-26	0.40649	22.9	9540	66166
+deu-khm	flores101-devtest	0.38800	2.3	1012	7006
+deu-vie	flores101-devtest	0.53381	33.8	1012	33331
+eng-khm	flores101-devtest	0.42302	1.3	1012	7006
+eng-vie	flores101-devtest	0.59621	42.1	1012	33331
+fra-khm	flores101-devtest	0.40042	2.2	1012	7006
+por-khm	flores101-devtest	0.40585	2.1	1012	7006
+por-vie	flores101-devtest	0.54919	36.0	1012	33331
+spa-khm	flores101-devtest	0.36844	1.3	1012	7006
+spa-vie	flores101-devtest	0.49921	27.8	1012	33331
+deu-khm	flores200-devtest	0.38953	2.4	1012	7006
+deu-sat	flores200-devtest	0.13449	0.1	1012	25693
+deu-vie	flores200-devtest	0.53671	34.0	1012	33331
+eng-khm	flores200-devtest	0.42148	1.3	1012	7006
+eng-sat	flores200-devtest	0.355	0.0	1012	25693
+eng-vie	flores200-devtest	0.59842	42.4	1012	33331
+fra-khm	flores200-devtest	0.39960	2.3	1012	7006
+fra-sat	flores200-devtest	0.13630	0.1	1012	25693
+fra-vie	flores200-devtest	0.54101	34.6	1012	33331
+por-khm	flores200-devtest	0.40832	1.9	1012	7006
+por-sat	flores200-devtest	0.13503	0.1	1012	25693
+por-vie	flores200-devtest	0.54970	36.1	1012	33331
+spa-khm	flores200-devtest	0.36868	1.4	1012	7006
+spa-sat	flores200-devtest	0.13742	0.1	1012	25693
+spa-vie	flores200-devtest	0.50025	28.1	1012	33331
+eng-khm	newstest2020	0.35104	0.9	2320	15454
+deu-khm	ntrex128	0.44903	3.5	1997	15866
+deu-vie	ntrex128	0.52124	31.4	1997	64655
+eng-khm	ntrex128	0.50494	1.6	1997	15866
+eng-vie	ntrex128	3.831	0.0	1997	64655
+fra-khm	ntrex128	0.43841	2.4	1997	15866
+fra-vie	ntrex128	0.52044	31.8	1997	64655
+por-khm	ntrex128	0.46655	2.5	1997	15866
+por-vie	ntrex128	0.53060	33.3	1997	64655
+spa-khm	ntrex128	0.46443	2.7	1997	15866
+spa-vie	ntrex128	0.53293	33.4	1997	64655
+eng-khm	tatoeba-test-v2020-07-28	0.34565	0.2	752	1737
+spa-khm	tatoeba-test-v2020-07-28	0.37159	0.2	1472	3391
+spa-vie	tatoeba-test-v2020-07-28	0.52030	34.2	582	4654
+deu-vie	tatoeba-test-v2021-03-30	0.45756	25.4	401	3775
+eng-hoc	tatoeba-test-v2021-03-30	6.373	0.2	661	2594
+eng-khm	tatoeba-test-v2021-03-30	0.34549	0.2	754	1741
+spa-khm	tatoeba-test-v2021-03-30	0.37159	0.2	1472	3391
+spa-vie	tatoeba-test-v2021-03-30	0.52010	34.3	604	4824
+deu-vie	tatoeba-test-v2021-08-07	0.45795	25.6	400	3768
+eng-hoc	tatoeba-test-v2021-08-07	6.438	0.2	660	2591
+eng-kha	tatoeba-test-v2021-08-07	5.741	0.0	1314	9269
+eng-khm	tatoeba-test-v2021-08-07	0.33850	0.2	726	1692
+eng-vie	tatoeba-test-v2021-08-07	0.56461	39.4	2500	24427
+fra-vie	tatoeba-test-v2021-08-07	0.52806	35.2	1299	13219
+spa-khm	tatoeba-test-v2021-08-07	0.37427	0.2	1448	3343
+spa-vie	tatoeba-test-v2021-08-07	0.52131	34.2	594	4740
+eng-khm	tico19-test	0.47806	2.5	2100	15810
+fra-khm	tico19-test	3.268	1.0	2100	15810
+por-khm	tico19-test	3.900	1.1	2100	15810
+spa-khm	tico19-test	3.784	1.0	2100	15810

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-aav",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 57538,
+  "decoder_vocab_size": 57539,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 943,
+  "forced_eos_token_id": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 57538,
+  "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": 57539
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      57538
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 57538,
+  "eos_token_id": 943,
+  "forced_eos_token_id": 943,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 57538,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43caecd953c319c06057ae84727f24a5441f39e463ae8d63799e9a0af8b1ba5
+size 941369020

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d6d94fd32087fe201bd6338b5703f8d5ff3ac1776c170faee97935156ec170
+size 941420293

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cc250d301ef587fcb7af9c7c5d4651ccb4f9a69deb0ebcc29f9e55e3bb8ca6
+size 803648

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:cb53816a56d71f4a8b3ccf5f3e6ada62b1107acae9c90b7b4c792108a9bc520e
+size 888156

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "deu+eng+fra+por+spa", "target_lang": "aav", "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/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29/deu+eng+fra+por+spa-aav", "tokenizer_class": "MarianTokenizer"}