Translation
Transformers
PyTorch
Safetensors
marian
text2text-generation
opus-mt-tc-bible
Eval Results (legacy)
Instructions to use WindstormLabs/origin-Helsinki-NLP-opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindstormLabs/origin-Helsinki-NLP-opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="WindstormLabs/origin-Helsinki-NLP-opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("WindstormLabs/origin-Helsinki-NLP-opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa") model = AutoModelForMultimodalLM.from_pretrained("WindstormLabs/origin-Helsinki-NLP-opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa") - Notebooks
- Google Colab
- Kaggle
upstream-archive byte-perfect snapshot of Helsinki-NLP/opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa (ADR-039 Phase D)
Browse files- .gitattributes +1 -0
- README.md +1357 -0
- benchmark_results.txt +89 -0
- benchmark_translations.zip +0 -0
- config.json +41 -0
- generation_config.json +16 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- source.spm +3 -0
- special_tokens_map.json +1 -0
- target.spm +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*.spm filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,1357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- bal
|
| 5 |
+
- de
|
| 6 |
+
- diq
|
| 7 |
+
- en
|
| 8 |
+
- es
|
| 9 |
+
- fa
|
| 10 |
+
- fr
|
| 11 |
+
- glk
|
| 12 |
+
- jdt
|
| 13 |
+
- ku
|
| 14 |
+
- lrc
|
| 15 |
+
- mzn
|
| 16 |
+
- os
|
| 17 |
+
- pal
|
| 18 |
+
- ps
|
| 19 |
+
- pt
|
| 20 |
+
- tg
|
| 21 |
+
- tly
|
| 22 |
+
- zza
|
| 23 |
+
language_bcp47:
|
| 24 |
+
- ku_Latn
|
| 25 |
+
|
| 26 |
+
tags:
|
| 27 |
+
- translation
|
| 28 |
+
- opus-mt-tc-bible
|
| 29 |
+
|
| 30 |
+
license: apache-2.0
|
| 31 |
+
model-index:
|
| 32 |
+
- name: opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa
|
| 33 |
+
results:
|
| 34 |
+
- task:
|
| 35 |
+
name: Translation ckb-deu
|
| 36 |
+
type: translation
|
| 37 |
+
args: ckb-deu
|
| 38 |
+
dataset:
|
| 39 |
+
name: flores200-devtest
|
| 40 |
+
type: flores200-devtest
|
| 41 |
+
args: ckb-deu
|
| 42 |
+
metrics:
|
| 43 |
+
- name: BLEU
|
| 44 |
+
type: bleu
|
| 45 |
+
value: 11.7
|
| 46 |
+
- name: chr-F
|
| 47 |
+
type: chrf
|
| 48 |
+
value: 0.40369
|
| 49 |
+
- task:
|
| 50 |
+
name: Translation ckb-eng
|
| 51 |
+
type: translation
|
| 52 |
+
args: ckb-eng
|
| 53 |
+
dataset:
|
| 54 |
+
name: flores200-devtest
|
| 55 |
+
type: flores200-devtest
|
| 56 |
+
args: ckb-eng
|
| 57 |
+
metrics:
|
| 58 |
+
- name: BLEU
|
| 59 |
+
type: bleu
|
| 60 |
+
value: 21.5
|
| 61 |
+
- name: chr-F
|
| 62 |
+
type: chrf
|
| 63 |
+
value: 0.48447
|
| 64 |
+
- task:
|
| 65 |
+
name: Translation ckb-fra
|
| 66 |
+
type: translation
|
| 67 |
+
args: ckb-fra
|
| 68 |
+
dataset:
|
| 69 |
+
name: flores200-devtest
|
| 70 |
+
type: flores200-devtest
|
| 71 |
+
args: ckb-fra
|
| 72 |
+
metrics:
|
| 73 |
+
- name: BLEU
|
| 74 |
+
type: bleu
|
| 75 |
+
value: 17.1
|
| 76 |
+
- name: chr-F
|
| 77 |
+
type: chrf
|
| 78 |
+
value: 0.44026
|
| 79 |
+
- task:
|
| 80 |
+
name: Translation ckb-por
|
| 81 |
+
type: translation
|
| 82 |
+
args: ckb-por
|
| 83 |
+
dataset:
|
| 84 |
+
name: flores200-devtest
|
| 85 |
+
type: flores200-devtest
|
| 86 |
+
args: ckb-por
|
| 87 |
+
metrics:
|
| 88 |
+
- name: BLEU
|
| 89 |
+
type: bleu
|
| 90 |
+
value: 16.4
|
| 91 |
+
- name: chr-F
|
| 92 |
+
type: chrf
|
| 93 |
+
value: 0.43192
|
| 94 |
+
- task:
|
| 95 |
+
name: Translation ckb-spa
|
| 96 |
+
type: translation
|
| 97 |
+
args: ckb-spa
|
| 98 |
+
dataset:
|
| 99 |
+
name: flores200-devtest
|
| 100 |
+
type: flores200-devtest
|
| 101 |
+
args: ckb-spa
|
| 102 |
+
metrics:
|
| 103 |
+
- name: BLEU
|
| 104 |
+
type: bleu
|
| 105 |
+
value: 11.7
|
| 106 |
+
- name: chr-F
|
| 107 |
+
type: chrf
|
| 108 |
+
value: 0.38880
|
| 109 |
+
- task:
|
| 110 |
+
name: Translation kmr-eng
|
| 111 |
+
type: translation
|
| 112 |
+
args: kmr-eng
|
| 113 |
+
dataset:
|
| 114 |
+
name: flores200-devtest
|
| 115 |
+
type: flores200-devtest
|
| 116 |
+
args: kmr-eng
|
| 117 |
+
metrics:
|
| 118 |
+
- name: BLEU
|
| 119 |
+
type: bleu
|
| 120 |
+
value: 12.4
|
| 121 |
+
- name: chr-F
|
| 122 |
+
type: chrf
|
| 123 |
+
value: 0.37372
|
| 124 |
+
- task:
|
| 125 |
+
name: Translation pes-deu
|
| 126 |
+
type: translation
|
| 127 |
+
args: pes-deu
|
| 128 |
+
dataset:
|
| 129 |
+
name: flores200-devtest
|
| 130 |
+
type: flores200-devtest
|
| 131 |
+
args: pes-deu
|
| 132 |
+
metrics:
|
| 133 |
+
- name: BLEU
|
| 134 |
+
type: bleu
|
| 135 |
+
value: 21.5
|
| 136 |
+
- name: chr-F
|
| 137 |
+
type: chrf
|
| 138 |
+
value: 0.51542
|
| 139 |
+
- task:
|
| 140 |
+
name: Translation pes-eng
|
| 141 |
+
type: translation
|
| 142 |
+
args: pes-eng
|
| 143 |
+
dataset:
|
| 144 |
+
name: flores200-devtest
|
| 145 |
+
type: flores200-devtest
|
| 146 |
+
args: pes-eng
|
| 147 |
+
metrics:
|
| 148 |
+
- name: BLEU
|
| 149 |
+
type: bleu
|
| 150 |
+
value: 34.9
|
| 151 |
+
- name: chr-F
|
| 152 |
+
type: chrf
|
| 153 |
+
value: 0.61372
|
| 154 |
+
- task:
|
| 155 |
+
name: Translation pes-fra
|
| 156 |
+
type: translation
|
| 157 |
+
args: pes-fra
|
| 158 |
+
dataset:
|
| 159 |
+
name: flores200-devtest
|
| 160 |
+
type: flores200-devtest
|
| 161 |
+
args: pes-fra
|
| 162 |
+
metrics:
|
| 163 |
+
- name: BLEU
|
| 164 |
+
type: bleu
|
| 165 |
+
value: 29.2
|
| 166 |
+
- name: chr-F
|
| 167 |
+
type: chrf
|
| 168 |
+
value: 0.56347
|
| 169 |
+
- task:
|
| 170 |
+
name: Translation pes-por
|
| 171 |
+
type: translation
|
| 172 |
+
args: pes-por
|
| 173 |
+
dataset:
|
| 174 |
+
name: flores200-devtest
|
| 175 |
+
type: flores200-devtest
|
| 176 |
+
args: pes-por
|
| 177 |
+
metrics:
|
| 178 |
+
- name: BLEU
|
| 179 |
+
type: bleu
|
| 180 |
+
value: 28.5
|
| 181 |
+
- name: chr-F
|
| 182 |
+
type: chrf
|
| 183 |
+
value: 0.55676
|
| 184 |
+
- task:
|
| 185 |
+
name: Translation pes-spa
|
| 186 |
+
type: translation
|
| 187 |
+
args: pes-spa
|
| 188 |
+
dataset:
|
| 189 |
+
name: flores200-devtest
|
| 190 |
+
type: flores200-devtest
|
| 191 |
+
args: pes-spa
|
| 192 |
+
metrics:
|
| 193 |
+
- name: BLEU
|
| 194 |
+
type: bleu
|
| 195 |
+
value: 19.8
|
| 196 |
+
- name: chr-F
|
| 197 |
+
type: chrf
|
| 198 |
+
value: 0.48334
|
| 199 |
+
- task:
|
| 200 |
+
name: Translation prs-deu
|
| 201 |
+
type: translation
|
| 202 |
+
args: prs-deu
|
| 203 |
+
dataset:
|
| 204 |
+
name: flores200-devtest
|
| 205 |
+
type: flores200-devtest
|
| 206 |
+
args: prs-deu
|
| 207 |
+
metrics:
|
| 208 |
+
- name: BLEU
|
| 209 |
+
type: bleu
|
| 210 |
+
value: 21.2
|
| 211 |
+
- name: chr-F
|
| 212 |
+
type: chrf
|
| 213 |
+
value: 0.50562
|
| 214 |
+
- task:
|
| 215 |
+
name: Translation prs-eng
|
| 216 |
+
type: translation
|
| 217 |
+
args: prs-eng
|
| 218 |
+
dataset:
|
| 219 |
+
name: flores200-devtest
|
| 220 |
+
type: flores200-devtest
|
| 221 |
+
args: prs-eng
|
| 222 |
+
metrics:
|
| 223 |
+
- name: BLEU
|
| 224 |
+
type: bleu
|
| 225 |
+
value: 35.1
|
| 226 |
+
- name: chr-F
|
| 227 |
+
type: chrf
|
| 228 |
+
value: 0.60716
|
| 229 |
+
- task:
|
| 230 |
+
name: Translation prs-fra
|
| 231 |
+
type: translation
|
| 232 |
+
args: prs-fra
|
| 233 |
+
dataset:
|
| 234 |
+
name: flores200-devtest
|
| 235 |
+
type: flores200-devtest
|
| 236 |
+
args: prs-fra
|
| 237 |
+
metrics:
|
| 238 |
+
- name: BLEU
|
| 239 |
+
type: bleu
|
| 240 |
+
value: 27.8
|
| 241 |
+
- name: chr-F
|
| 242 |
+
type: chrf
|
| 243 |
+
value: 0.54769
|
| 244 |
+
- task:
|
| 245 |
+
name: Translation prs-por
|
| 246 |
+
type: translation
|
| 247 |
+
args: prs-por
|
| 248 |
+
dataset:
|
| 249 |
+
name: flores200-devtest
|
| 250 |
+
type: flores200-devtest
|
| 251 |
+
args: prs-por
|
| 252 |
+
metrics:
|
| 253 |
+
- name: BLEU
|
| 254 |
+
type: bleu
|
| 255 |
+
value: 27.2
|
| 256 |
+
- name: chr-F
|
| 257 |
+
type: chrf
|
| 258 |
+
value: 0.54073
|
| 259 |
+
- task:
|
| 260 |
+
name: Translation prs-spa
|
| 261 |
+
type: translation
|
| 262 |
+
args: prs-spa
|
| 263 |
+
dataset:
|
| 264 |
+
name: flores200-devtest
|
| 265 |
+
type: flores200-devtest
|
| 266 |
+
args: prs-spa
|
| 267 |
+
metrics:
|
| 268 |
+
- name: BLEU
|
| 269 |
+
type: bleu
|
| 270 |
+
value: 18.6
|
| 271 |
+
- name: chr-F
|
| 272 |
+
type: chrf
|
| 273 |
+
value: 0.46850
|
| 274 |
+
- task:
|
| 275 |
+
name: Translation tgk-deu
|
| 276 |
+
type: translation
|
| 277 |
+
args: tgk-deu
|
| 278 |
+
dataset:
|
| 279 |
+
name: flores200-devtest
|
| 280 |
+
type: flores200-devtest
|
| 281 |
+
args: tgk-deu
|
| 282 |
+
metrics:
|
| 283 |
+
- name: BLEU
|
| 284 |
+
type: bleu
|
| 285 |
+
value: 14.2
|
| 286 |
+
- name: chr-F
|
| 287 |
+
type: chrf
|
| 288 |
+
value: 0.43115
|
| 289 |
+
- task:
|
| 290 |
+
name: Translation tgk-eng
|
| 291 |
+
type: translation
|
| 292 |
+
args: tgk-eng
|
| 293 |
+
dataset:
|
| 294 |
+
name: flores200-devtest
|
| 295 |
+
type: flores200-devtest
|
| 296 |
+
args: tgk-eng
|
| 297 |
+
metrics:
|
| 298 |
+
- name: BLEU
|
| 299 |
+
type: bleu
|
| 300 |
+
value: 25.6
|
| 301 |
+
- name: chr-F
|
| 302 |
+
type: chrf
|
| 303 |
+
value: 0.53705
|
| 304 |
+
- task:
|
| 305 |
+
name: Translation tgk-fra
|
| 306 |
+
type: translation
|
| 307 |
+
args: tgk-fra
|
| 308 |
+
dataset:
|
| 309 |
+
name: flores200-devtest
|
| 310 |
+
type: flores200-devtest
|
| 311 |
+
args: tgk-fra
|
| 312 |
+
metrics:
|
| 313 |
+
- name: BLEU
|
| 314 |
+
type: bleu
|
| 315 |
+
value: 20.7
|
| 316 |
+
- name: chr-F
|
| 317 |
+
type: chrf
|
| 318 |
+
value: 0.48902
|
| 319 |
+
- task:
|
| 320 |
+
name: Translation tgk-por
|
| 321 |
+
type: translation
|
| 322 |
+
args: tgk-por
|
| 323 |
+
dataset:
|
| 324 |
+
name: flores200-devtest
|
| 325 |
+
type: flores200-devtest
|
| 326 |
+
args: tgk-por
|
| 327 |
+
metrics:
|
| 328 |
+
- name: BLEU
|
| 329 |
+
type: bleu
|
| 330 |
+
value: 20.7
|
| 331 |
+
- name: chr-F
|
| 332 |
+
type: chrf
|
| 333 |
+
value: 0.48519
|
| 334 |
+
- task:
|
| 335 |
+
name: Translation tgk-spa
|
| 336 |
+
type: translation
|
| 337 |
+
args: tgk-spa
|
| 338 |
+
dataset:
|
| 339 |
+
name: flores200-devtest
|
| 340 |
+
type: flores200-devtest
|
| 341 |
+
args: tgk-spa
|
| 342 |
+
metrics:
|
| 343 |
+
- name: BLEU
|
| 344 |
+
type: bleu
|
| 345 |
+
value: 15.7
|
| 346 |
+
- name: chr-F
|
| 347 |
+
type: chrf
|
| 348 |
+
value: 0.43563
|
| 349 |
+
- task:
|
| 350 |
+
name: Translation ckb-deu
|
| 351 |
+
type: translation
|
| 352 |
+
args: ckb-deu
|
| 353 |
+
dataset:
|
| 354 |
+
name: flores101-devtest
|
| 355 |
+
type: flores_101
|
| 356 |
+
args: ckb deu devtest
|
| 357 |
+
metrics:
|
| 358 |
+
- name: BLEU
|
| 359 |
+
type: bleu
|
| 360 |
+
value: 11.6
|
| 361 |
+
- name: chr-F
|
| 362 |
+
type: chrf
|
| 363 |
+
value: 0.40117
|
| 364 |
+
- task:
|
| 365 |
+
name: Translation ckb-eng
|
| 366 |
+
type: translation
|
| 367 |
+
args: ckb-eng
|
| 368 |
+
dataset:
|
| 369 |
+
name: flores101-devtest
|
| 370 |
+
type: flores_101
|
| 371 |
+
args: ckb eng devtest
|
| 372 |
+
metrics:
|
| 373 |
+
- name: BLEU
|
| 374 |
+
type: bleu
|
| 375 |
+
value: 21.6
|
| 376 |
+
- name: chr-F
|
| 377 |
+
type: chrf
|
| 378 |
+
value: 0.48321
|
| 379 |
+
- task:
|
| 380 |
+
name: Translation ckb-fra
|
| 381 |
+
type: translation
|
| 382 |
+
args: ckb-fra
|
| 383 |
+
dataset:
|
| 384 |
+
name: flores101-devtest
|
| 385 |
+
type: flores_101
|
| 386 |
+
args: ckb fra devtest
|
| 387 |
+
metrics:
|
| 388 |
+
- name: BLEU
|
| 389 |
+
type: bleu
|
| 390 |
+
value: 17.2
|
| 391 |
+
- name: chr-F
|
| 392 |
+
type: chrf
|
| 393 |
+
value: 0.44260
|
| 394 |
+
- task:
|
| 395 |
+
name: Translation ckb-por
|
| 396 |
+
type: translation
|
| 397 |
+
args: ckb-por
|
| 398 |
+
dataset:
|
| 399 |
+
name: flores101-devtest
|
| 400 |
+
type: flores_101
|
| 401 |
+
args: ckb por devtest
|
| 402 |
+
metrics:
|
| 403 |
+
- name: BLEU
|
| 404 |
+
type: bleu
|
| 405 |
+
value: 16.2
|
| 406 |
+
- name: chr-F
|
| 407 |
+
type: chrf
|
| 408 |
+
value: 0.43179
|
| 409 |
+
- task:
|
| 410 |
+
name: Translation fas-eng
|
| 411 |
+
type: translation
|
| 412 |
+
args: fas-eng
|
| 413 |
+
dataset:
|
| 414 |
+
name: flores101-devtest
|
| 415 |
+
type: flores_101
|
| 416 |
+
args: fas eng devtest
|
| 417 |
+
metrics:
|
| 418 |
+
- name: BLEU
|
| 419 |
+
type: bleu
|
| 420 |
+
value: 34.4
|
| 421 |
+
- name: chr-F
|
| 422 |
+
type: chrf
|
| 423 |
+
value: 0.61134
|
| 424 |
+
- task:
|
| 425 |
+
name: Translation pus-eng
|
| 426 |
+
type: translation
|
| 427 |
+
args: pus-eng
|
| 428 |
+
dataset:
|
| 429 |
+
name: flores101-devtest
|
| 430 |
+
type: flores_101
|
| 431 |
+
args: pus eng devtest
|
| 432 |
+
metrics:
|
| 433 |
+
- name: BLEU
|
| 434 |
+
type: bleu
|
| 435 |
+
value: 22.7
|
| 436 |
+
- name: chr-F
|
| 437 |
+
type: chrf
|
| 438 |
+
value: 0.49556
|
| 439 |
+
- task:
|
| 440 |
+
name: Translation pus-fra
|
| 441 |
+
type: translation
|
| 442 |
+
args: pus-fra
|
| 443 |
+
dataset:
|
| 444 |
+
name: flores101-devtest
|
| 445 |
+
type: flores_101
|
| 446 |
+
args: pus fra devtest
|
| 447 |
+
metrics:
|
| 448 |
+
- name: BLEU
|
| 449 |
+
type: bleu
|
| 450 |
+
value: 17.8
|
| 451 |
+
- name: chr-F
|
| 452 |
+
type: chrf
|
| 453 |
+
value: 0.45248
|
| 454 |
+
- task:
|
| 455 |
+
name: Translation tgk-eng
|
| 456 |
+
type: translation
|
| 457 |
+
args: tgk-eng
|
| 458 |
+
dataset:
|
| 459 |
+
name: flores101-devtest
|
| 460 |
+
type: flores_101
|
| 461 |
+
args: tgk eng devtest
|
| 462 |
+
metrics:
|
| 463 |
+
- name: BLEU
|
| 464 |
+
type: bleu
|
| 465 |
+
value: 25.4
|
| 466 |
+
- name: chr-F
|
| 467 |
+
type: chrf
|
| 468 |
+
value: 0.53630
|
| 469 |
+
- task:
|
| 470 |
+
name: Translation tgk-fra
|
| 471 |
+
type: translation
|
| 472 |
+
args: tgk-fra
|
| 473 |
+
dataset:
|
| 474 |
+
name: flores101-devtest
|
| 475 |
+
type: flores_101
|
| 476 |
+
args: tgk fra devtest
|
| 477 |
+
metrics:
|
| 478 |
+
- name: BLEU
|
| 479 |
+
type: bleu
|
| 480 |
+
value: 21.0
|
| 481 |
+
- name: chr-F
|
| 482 |
+
type: chrf
|
| 483 |
+
value: 0.49084
|
| 484 |
+
- task:
|
| 485 |
+
name: Translation tgk-spa
|
| 486 |
+
type: translation
|
| 487 |
+
args: tgk-spa
|
| 488 |
+
dataset:
|
| 489 |
+
name: flores101-devtest
|
| 490 |
+
type: flores_101
|
| 491 |
+
args: tgk spa devtest
|
| 492 |
+
metrics:
|
| 493 |
+
- name: BLEU
|
| 494 |
+
type: bleu
|
| 495 |
+
value: 15.5
|
| 496 |
+
- name: chr-F
|
| 497 |
+
type: chrf
|
| 498 |
+
value: 0.43524
|
| 499 |
+
- task:
|
| 500 |
+
name: Translation fas-deu
|
| 501 |
+
type: translation
|
| 502 |
+
args: fas-deu
|
| 503 |
+
dataset:
|
| 504 |
+
name: ntrex128
|
| 505 |
+
type: ntrex128
|
| 506 |
+
args: fas-deu
|
| 507 |
+
metrics:
|
| 508 |
+
- name: BLEU
|
| 509 |
+
type: bleu
|
| 510 |
+
value: 16.7
|
| 511 |
+
- name: chr-F
|
| 512 |
+
type: chrf
|
| 513 |
+
value: 0.47408
|
| 514 |
+
- task:
|
| 515 |
+
name: Translation fas-eng
|
| 516 |
+
type: translation
|
| 517 |
+
args: fas-eng
|
| 518 |
+
dataset:
|
| 519 |
+
name: ntrex128
|
| 520 |
+
type: ntrex128
|
| 521 |
+
args: fas-eng
|
| 522 |
+
metrics:
|
| 523 |
+
- name: BLEU
|
| 524 |
+
type: bleu
|
| 525 |
+
value: 26.4
|
| 526 |
+
- name: chr-F
|
| 527 |
+
type: chrf
|
| 528 |
+
value: 0.55350
|
| 529 |
+
- task:
|
| 530 |
+
name: Translation fas-fra
|
| 531 |
+
type: translation
|
| 532 |
+
args: fas-fra
|
| 533 |
+
dataset:
|
| 534 |
+
name: ntrex128
|
| 535 |
+
type: ntrex128
|
| 536 |
+
args: fas-fra
|
| 537 |
+
metrics:
|
| 538 |
+
- name: BLEU
|
| 539 |
+
type: bleu
|
| 540 |
+
value: 22.1
|
| 541 |
+
- name: chr-F
|
| 542 |
+
type: chrf
|
| 543 |
+
value: 0.50311
|
| 544 |
+
- task:
|
| 545 |
+
name: Translation fas-por
|
| 546 |
+
type: translation
|
| 547 |
+
args: fas-por
|
| 548 |
+
dataset:
|
| 549 |
+
name: ntrex128
|
| 550 |
+
type: ntrex128
|
| 551 |
+
args: fas-por
|
| 552 |
+
metrics:
|
| 553 |
+
- name: BLEU
|
| 554 |
+
type: bleu
|
| 555 |
+
value: 19.1
|
| 556 |
+
- name: chr-F
|
| 557 |
+
type: chrf
|
| 558 |
+
value: 0.48005
|
| 559 |
+
- task:
|
| 560 |
+
name: Translation fas-spa
|
| 561 |
+
type: translation
|
| 562 |
+
args: fas-spa
|
| 563 |
+
dataset:
|
| 564 |
+
name: ntrex128
|
| 565 |
+
type: ntrex128
|
| 566 |
+
args: fas-spa
|
| 567 |
+
metrics:
|
| 568 |
+
- name: BLEU
|
| 569 |
+
type: bleu
|
| 570 |
+
value: 23.6
|
| 571 |
+
- name: chr-F
|
| 572 |
+
type: chrf
|
| 573 |
+
value: 0.50973
|
| 574 |
+
- task:
|
| 575 |
+
name: Translation kmr-eng
|
| 576 |
+
type: translation
|
| 577 |
+
args: kmr-eng
|
| 578 |
+
dataset:
|
| 579 |
+
name: ntrex128
|
| 580 |
+
type: ntrex128
|
| 581 |
+
args: kmr-eng
|
| 582 |
+
metrics:
|
| 583 |
+
- name: BLEU
|
| 584 |
+
type: bleu
|
| 585 |
+
value: 12.8
|
| 586 |
+
- name: chr-F
|
| 587 |
+
type: chrf
|
| 588 |
+
value: 0.38189
|
| 589 |
+
- task:
|
| 590 |
+
name: Translation prs-deu
|
| 591 |
+
type: translation
|
| 592 |
+
args: prs-deu
|
| 593 |
+
dataset:
|
| 594 |
+
name: ntrex128
|
| 595 |
+
type: ntrex128
|
| 596 |
+
args: prs-deu
|
| 597 |
+
metrics:
|
| 598 |
+
- name: BLEU
|
| 599 |
+
type: bleu
|
| 600 |
+
value: 14.9
|
| 601 |
+
- name: chr-F
|
| 602 |
+
type: chrf
|
| 603 |
+
value: 0.45191
|
| 604 |
+
- task:
|
| 605 |
+
name: Translation prs-eng
|
| 606 |
+
type: translation
|
| 607 |
+
args: prs-eng
|
| 608 |
+
dataset:
|
| 609 |
+
name: ntrex128
|
| 610 |
+
type: ntrex128
|
| 611 |
+
args: prs-eng
|
| 612 |
+
metrics:
|
| 613 |
+
- name: BLEU
|
| 614 |
+
type: bleu
|
| 615 |
+
value: 26.6
|
| 616 |
+
- name: chr-F
|
| 617 |
+
type: chrf
|
| 618 |
+
value: 0.54761
|
| 619 |
+
- task:
|
| 620 |
+
name: Translation prs-fra
|
| 621 |
+
type: translation
|
| 622 |
+
args: prs-fra
|
| 623 |
+
dataset:
|
| 624 |
+
name: ntrex128
|
| 625 |
+
type: ntrex128
|
| 626 |
+
args: prs-fra
|
| 627 |
+
metrics:
|
| 628 |
+
- name: BLEU
|
| 629 |
+
type: bleu
|
| 630 |
+
value: 19.9
|
| 631 |
+
- name: chr-F
|
| 632 |
+
type: chrf
|
| 633 |
+
value: 0.47819
|
| 634 |
+
- task:
|
| 635 |
+
name: Translation prs-por
|
| 636 |
+
type: translation
|
| 637 |
+
args: prs-por
|
| 638 |
+
dataset:
|
| 639 |
+
name: ntrex128
|
| 640 |
+
type: ntrex128
|
| 641 |
+
args: prs-por
|
| 642 |
+
metrics:
|
| 643 |
+
- name: BLEU
|
| 644 |
+
type: bleu
|
| 645 |
+
value: 17.4
|
| 646 |
+
- name: chr-F
|
| 647 |
+
type: chrf
|
| 648 |
+
value: 0.46241
|
| 649 |
+
- task:
|
| 650 |
+
name: Translation prs-spa
|
| 651 |
+
type: translation
|
| 652 |
+
args: prs-spa
|
| 653 |
+
dataset:
|
| 654 |
+
name: ntrex128
|
| 655 |
+
type: ntrex128
|
| 656 |
+
args: prs-spa
|
| 657 |
+
metrics:
|
| 658 |
+
- name: BLEU
|
| 659 |
+
type: bleu
|
| 660 |
+
value: 21.4
|
| 661 |
+
- name: chr-F
|
| 662 |
+
type: chrf
|
| 663 |
+
value: 0.48712
|
| 664 |
+
- task:
|
| 665 |
+
name: Translation pus-eng
|
| 666 |
+
type: translation
|
| 667 |
+
args: pus-eng
|
| 668 |
+
dataset:
|
| 669 |
+
name: ntrex128
|
| 670 |
+
type: ntrex128
|
| 671 |
+
args: pus-eng
|
| 672 |
+
metrics:
|
| 673 |
+
- name: BLEU
|
| 674 |
+
type: bleu
|
| 675 |
+
value: 17.4
|
| 676 |
+
- name: chr-F
|
| 677 |
+
type: chrf
|
| 678 |
+
value: 0.43901
|
| 679 |
+
- task:
|
| 680 |
+
name: Translation pus-fra
|
| 681 |
+
type: translation
|
| 682 |
+
args: pus-fra
|
| 683 |
+
dataset:
|
| 684 |
+
name: ntrex128
|
| 685 |
+
type: ntrex128
|
| 686 |
+
args: pus-fra
|
| 687 |
+
metrics:
|
| 688 |
+
- name: BLEU
|
| 689 |
+
type: bleu
|
| 690 |
+
value: 12.4
|
| 691 |
+
- name: chr-F
|
| 692 |
+
type: chrf
|
| 693 |
+
value: 0.39661
|
| 694 |
+
- task:
|
| 695 |
+
name: Translation pus-por
|
| 696 |
+
type: translation
|
| 697 |
+
args: pus-por
|
| 698 |
+
dataset:
|
| 699 |
+
name: ntrex128
|
| 700 |
+
type: ntrex128
|
| 701 |
+
args: pus-por
|
| 702 |
+
metrics:
|
| 703 |
+
- name: BLEU
|
| 704 |
+
type: bleu
|
| 705 |
+
value: 11.4
|
| 706 |
+
- name: chr-F
|
| 707 |
+
type: chrf
|
| 708 |
+
value: 0.38694
|
| 709 |
+
- task:
|
| 710 |
+
name: Translation pus-spa
|
| 711 |
+
type: translation
|
| 712 |
+
args: pus-spa
|
| 713 |
+
dataset:
|
| 714 |
+
name: ntrex128
|
| 715 |
+
type: ntrex128
|
| 716 |
+
args: pus-spa
|
| 717 |
+
metrics:
|
| 718 |
+
- name: BLEU
|
| 719 |
+
type: bleu
|
| 720 |
+
value: 14.1
|
| 721 |
+
- name: chr-F
|
| 722 |
+
type: chrf
|
| 723 |
+
value: 0.40812
|
| 724 |
+
- task:
|
| 725 |
+
name: Translation tgk_Cyrl-deu
|
| 726 |
+
type: translation
|
| 727 |
+
args: tgk_Cyrl-deu
|
| 728 |
+
dataset:
|
| 729 |
+
name: ntrex128
|
| 730 |
+
type: ntrex128
|
| 731 |
+
args: tgk_Cyrl-deu
|
| 732 |
+
metrics:
|
| 733 |
+
- name: BLEU
|
| 734 |
+
type: bleu
|
| 735 |
+
value: 10.7
|
| 736 |
+
- name: chr-F
|
| 737 |
+
type: chrf
|
| 738 |
+
value: 0.38740
|
| 739 |
+
- task:
|
| 740 |
+
name: Translation tgk_Cyrl-eng
|
| 741 |
+
type: translation
|
| 742 |
+
args: tgk_Cyrl-eng
|
| 743 |
+
dataset:
|
| 744 |
+
name: ntrex128
|
| 745 |
+
type: ntrex128
|
| 746 |
+
args: tgk_Cyrl-eng
|
| 747 |
+
metrics:
|
| 748 |
+
- name: BLEU
|
| 749 |
+
type: bleu
|
| 750 |
+
value: 18.6
|
| 751 |
+
- name: chr-F
|
| 752 |
+
type: chrf
|
| 753 |
+
value: 0.46839
|
| 754 |
+
- task:
|
| 755 |
+
name: Translation tgk_Cyrl-fra
|
| 756 |
+
type: translation
|
| 757 |
+
args: tgk_Cyrl-fra
|
| 758 |
+
dataset:
|
| 759 |
+
name: ntrex128
|
| 760 |
+
type: ntrex128
|
| 761 |
+
args: tgk_Cyrl-fra
|
| 762 |
+
metrics:
|
| 763 |
+
- name: BLEU
|
| 764 |
+
type: bleu
|
| 765 |
+
value: 15.1
|
| 766 |
+
- name: chr-F
|
| 767 |
+
type: chrf
|
| 768 |
+
value: 0.42569
|
| 769 |
+
- task:
|
| 770 |
+
name: Translation tgk_Cyrl-por
|
| 771 |
+
type: translation
|
| 772 |
+
args: tgk_Cyrl-por
|
| 773 |
+
dataset:
|
| 774 |
+
name: ntrex128
|
| 775 |
+
type: ntrex128
|
| 776 |
+
args: tgk_Cyrl-por
|
| 777 |
+
metrics:
|
| 778 |
+
- name: BLEU
|
| 779 |
+
type: bleu
|
| 780 |
+
value: 13.7
|
| 781 |
+
- name: chr-F
|
| 782 |
+
type: chrf
|
| 783 |
+
value: 0.41632
|
| 784 |
+
- task:
|
| 785 |
+
name: Translation tgk_Cyrl-spa
|
| 786 |
+
type: translation
|
| 787 |
+
args: tgk_Cyrl-spa
|
| 788 |
+
dataset:
|
| 789 |
+
name: ntrex128
|
| 790 |
+
type: ntrex128
|
| 791 |
+
args: tgk_Cyrl-spa
|
| 792 |
+
metrics:
|
| 793 |
+
- name: BLEU
|
| 794 |
+
type: bleu
|
| 795 |
+
value: 16.8
|
| 796 |
+
- name: chr-F
|
| 797 |
+
type: chrf
|
| 798 |
+
value: 0.43763
|
| 799 |
+
- task:
|
| 800 |
+
name: Translation fas-deu
|
| 801 |
+
type: translation
|
| 802 |
+
args: fas-deu
|
| 803 |
+
dataset:
|
| 804 |
+
name: tatoeba-test-v2021-08-07
|
| 805 |
+
type: tatoeba_mt
|
| 806 |
+
args: fas-deu
|
| 807 |
+
metrics:
|
| 808 |
+
- name: BLEU
|
| 809 |
+
type: bleu
|
| 810 |
+
value: 36.1
|
| 811 |
+
- name: chr-F
|
| 812 |
+
type: chrf
|
| 813 |
+
value: 0.59737
|
| 814 |
+
- task:
|
| 815 |
+
name: Translation fas-eng
|
| 816 |
+
type: translation
|
| 817 |
+
args: fas-eng
|
| 818 |
+
dataset:
|
| 819 |
+
name: tatoeba-test-v2021-08-07
|
| 820 |
+
type: tatoeba_mt
|
| 821 |
+
args: fas-eng
|
| 822 |
+
metrics:
|
| 823 |
+
- name: BLEU
|
| 824 |
+
type: bleu
|
| 825 |
+
value: 35.8
|
| 826 |
+
- name: chr-F
|
| 827 |
+
type: chrf
|
| 828 |
+
value: 0.59871
|
| 829 |
+
- task:
|
| 830 |
+
name: Translation fas-fra
|
| 831 |
+
type: translation
|
| 832 |
+
args: fas-fra
|
| 833 |
+
dataset:
|
| 834 |
+
name: tatoeba-test-v2021-08-07
|
| 835 |
+
type: tatoeba_mt
|
| 836 |
+
args: fas-fra
|
| 837 |
+
metrics:
|
| 838 |
+
- name: BLEU
|
| 839 |
+
type: bleu
|
| 840 |
+
value: 36.3
|
| 841 |
+
- name: chr-F
|
| 842 |
+
type: chrf
|
| 843 |
+
value: 0.58095
|
| 844 |
+
- task:
|
| 845 |
+
name: Translation kur_Latn-deu
|
| 846 |
+
type: translation
|
| 847 |
+
args: kur_Latn-deu
|
| 848 |
+
dataset:
|
| 849 |
+
name: tatoeba-test-v2021-08-07
|
| 850 |
+
type: tatoeba_mt
|
| 851 |
+
args: kur_Latn-deu
|
| 852 |
+
metrics:
|
| 853 |
+
- name: BLEU
|
| 854 |
+
type: bleu
|
| 855 |
+
value: 24.9
|
| 856 |
+
- name: chr-F
|
| 857 |
+
type: chrf
|
| 858 |
+
value: 0.40276
|
| 859 |
+
- task:
|
| 860 |
+
name: Translation multi-multi
|
| 861 |
+
type: translation
|
| 862 |
+
args: multi-multi
|
| 863 |
+
dataset:
|
| 864 |
+
name: tatoeba-test-v2020-07-28-v2023-09-26
|
| 865 |
+
type: tatoeba_mt
|
| 866 |
+
args: multi-multi
|
| 867 |
+
metrics:
|
| 868 |
+
- name: BLEU
|
| 869 |
+
type: bleu
|
| 870 |
+
value: 34.0
|
| 871 |
+
- name: chr-F
|
| 872 |
+
type: chrf
|
| 873 |
+
value: 0.56042
|
| 874 |
+
- task:
|
| 875 |
+
name: Translation pes-eng
|
| 876 |
+
type: translation
|
| 877 |
+
args: pes-eng
|
| 878 |
+
dataset:
|
| 879 |
+
name: tatoeba-test-v2021-08-07
|
| 880 |
+
type: tatoeba_mt
|
| 881 |
+
args: pes-eng
|
| 882 |
+
metrics:
|
| 883 |
+
- name: BLEU
|
| 884 |
+
type: bleu
|
| 885 |
+
value: 42.3
|
| 886 |
+
- name: chr-F
|
| 887 |
+
type: chrf
|
| 888 |
+
value: 0.60717
|
| 889 |
+
- task:
|
| 890 |
+
name: Translation ckb-eng
|
| 891 |
+
type: translation
|
| 892 |
+
args: ckb-eng
|
| 893 |
+
dataset:
|
| 894 |
+
name: tico19-test
|
| 895 |
+
type: tico19-test
|
| 896 |
+
args: ckb-eng
|
| 897 |
+
metrics:
|
| 898 |
+
- name: BLEU
|
| 899 |
+
type: bleu
|
| 900 |
+
value: 40.1
|
| 901 |
+
- name: chr-F
|
| 902 |
+
type: chrf
|
| 903 |
+
value: 0.61905
|
| 904 |
+
- task:
|
| 905 |
+
name: Translation ckb-fra
|
| 906 |
+
type: translation
|
| 907 |
+
args: ckb-fra
|
| 908 |
+
dataset:
|
| 909 |
+
name: tico19-test
|
| 910 |
+
type: tico19-test
|
| 911 |
+
args: ckb-fra
|
| 912 |
+
metrics:
|
| 913 |
+
- name: BLEU
|
| 914 |
+
type: bleu
|
| 915 |
+
value: 19.7
|
| 916 |
+
- name: chr-F
|
| 917 |
+
type: chrf
|
| 918 |
+
value: 0.45070
|
| 919 |
+
- task:
|
| 920 |
+
name: Translation ckb-por
|
| 921 |
+
type: translation
|
| 922 |
+
args: ckb-por
|
| 923 |
+
dataset:
|
| 924 |
+
name: tico19-test
|
| 925 |
+
type: tico19-test
|
| 926 |
+
args: ckb-por
|
| 927 |
+
metrics:
|
| 928 |
+
- name: BLEU
|
| 929 |
+
type: bleu
|
| 930 |
+
value: 22.9
|
| 931 |
+
- name: chr-F
|
| 932 |
+
type: chrf
|
| 933 |
+
value: 0.49617
|
| 934 |
+
- task:
|
| 935 |
+
name: Translation ckb-spa
|
| 936 |
+
type: translation
|
| 937 |
+
args: ckb-spa
|
| 938 |
+
dataset:
|
| 939 |
+
name: tico19-test
|
| 940 |
+
type: tico19-test
|
| 941 |
+
args: ckb-spa
|
| 942 |
+
metrics:
|
| 943 |
+
- name: BLEU
|
| 944 |
+
type: bleu
|
| 945 |
+
value: 24.9
|
| 946 |
+
- name: chr-F
|
| 947 |
+
type: chrf
|
| 948 |
+
value: 0.50543
|
| 949 |
+
- task:
|
| 950 |
+
name: Translation fas-eng
|
| 951 |
+
type: translation
|
| 952 |
+
args: fas-eng
|
| 953 |
+
dataset:
|
| 954 |
+
name: tico19-test
|
| 955 |
+
type: tico19-test
|
| 956 |
+
args: fas-eng
|
| 957 |
+
metrics:
|
| 958 |
+
- name: BLEU
|
| 959 |
+
type: bleu
|
| 960 |
+
value: 37.3
|
| 961 |
+
- name: chr-F
|
| 962 |
+
type: chrf
|
| 963 |
+
value: 0.64016
|
| 964 |
+
- task:
|
| 965 |
+
name: Translation fas-fra
|
| 966 |
+
type: translation
|
| 967 |
+
args: fas-fra
|
| 968 |
+
dataset:
|
| 969 |
+
name: tico19-test
|
| 970 |
+
type: tico19-test
|
| 971 |
+
args: fas-fra
|
| 972 |
+
metrics:
|
| 973 |
+
- name: BLEU
|
| 974 |
+
type: bleu
|
| 975 |
+
value: 26.1
|
| 976 |
+
- name: chr-F
|
| 977 |
+
type: chrf
|
| 978 |
+
value: 0.53319
|
| 979 |
+
- task:
|
| 980 |
+
name: Translation fas-por
|
| 981 |
+
type: translation
|
| 982 |
+
args: fas-por
|
| 983 |
+
dataset:
|
| 984 |
+
name: tico19-test
|
| 985 |
+
type: tico19-test
|
| 986 |
+
args: fas-por
|
| 987 |
+
metrics:
|
| 988 |
+
- name: BLEU
|
| 989 |
+
type: bleu
|
| 990 |
+
value: 30.6
|
| 991 |
+
- name: chr-F
|
| 992 |
+
type: chrf
|
| 993 |
+
value: 0.58008
|
| 994 |
+
- task:
|
| 995 |
+
name: Translation fas-spa
|
| 996 |
+
type: translation
|
| 997 |
+
args: fas-spa
|
| 998 |
+
dataset:
|
| 999 |
+
name: tico19-test
|
| 1000 |
+
type: tico19-test
|
| 1001 |
+
args: fas-spa
|
| 1002 |
+
metrics:
|
| 1003 |
+
- name: BLEU
|
| 1004 |
+
type: bleu
|
| 1005 |
+
value: 33.3
|
| 1006 |
+
- name: chr-F
|
| 1007 |
+
type: chrf
|
| 1008 |
+
value: 0.59239
|
| 1009 |
+
- task:
|
| 1010 |
+
name: Translation prs-eng
|
| 1011 |
+
type: translation
|
| 1012 |
+
args: prs-eng
|
| 1013 |
+
dataset:
|
| 1014 |
+
name: tico19-test
|
| 1015 |
+
type: tico19-test
|
| 1016 |
+
args: prs-eng
|
| 1017 |
+
metrics:
|
| 1018 |
+
- name: BLEU
|
| 1019 |
+
type: bleu
|
| 1020 |
+
value: 34.8
|
| 1021 |
+
- name: chr-F
|
| 1022 |
+
type: chrf
|
| 1023 |
+
value: 0.61702
|
| 1024 |
+
- task:
|
| 1025 |
+
name: Translation prs-fra
|
| 1026 |
+
type: translation
|
| 1027 |
+
args: prs-fra
|
| 1028 |
+
dataset:
|
| 1029 |
+
name: tico19-test
|
| 1030 |
+
type: tico19-test
|
| 1031 |
+
args: prs-fra
|
| 1032 |
+
metrics:
|
| 1033 |
+
- name: BLEU
|
| 1034 |
+
type: bleu
|
| 1035 |
+
value: 24.0
|
| 1036 |
+
- name: chr-F
|
| 1037 |
+
type: chrf
|
| 1038 |
+
value: 0.51218
|
| 1039 |
+
- task:
|
| 1040 |
+
name: Translation prs-por
|
| 1041 |
+
type: translation
|
| 1042 |
+
args: prs-por
|
| 1043 |
+
dataset:
|
| 1044 |
+
name: tico19-test
|
| 1045 |
+
type: tico19-test
|
| 1046 |
+
args: prs-por
|
| 1047 |
+
metrics:
|
| 1048 |
+
- name: BLEU
|
| 1049 |
+
type: bleu
|
| 1050 |
+
value: 28.6
|
| 1051 |
+
- name: chr-F
|
| 1052 |
+
type: chrf
|
| 1053 |
+
value: 0.55888
|
| 1054 |
+
- task:
|
| 1055 |
+
name: Translation prs-spa
|
| 1056 |
+
type: translation
|
| 1057 |
+
args: prs-spa
|
| 1058 |
+
dataset:
|
| 1059 |
+
name: tico19-test
|
| 1060 |
+
type: tico19-test
|
| 1061 |
+
args: prs-spa
|
| 1062 |
+
metrics:
|
| 1063 |
+
- name: BLEU
|
| 1064 |
+
type: bleu
|
| 1065 |
+
value: 31.1
|
| 1066 |
+
- name: chr-F
|
| 1067 |
+
type: chrf
|
| 1068 |
+
value: 0.57494
|
| 1069 |
+
- task:
|
| 1070 |
+
name: Translation pus-eng
|
| 1071 |
+
type: translation
|
| 1072 |
+
args: pus-eng
|
| 1073 |
+
dataset:
|
| 1074 |
+
name: tico19-test
|
| 1075 |
+
type: tico19-test
|
| 1076 |
+
args: pus-eng
|
| 1077 |
+
metrics:
|
| 1078 |
+
- name: BLEU
|
| 1079 |
+
type: bleu
|
| 1080 |
+
value: 32.1
|
| 1081 |
+
- name: chr-F
|
| 1082 |
+
type: chrf
|
| 1083 |
+
value: 0.57586
|
| 1084 |
+
- task:
|
| 1085 |
+
name: Translation pus-fra
|
| 1086 |
+
type: translation
|
| 1087 |
+
args: pus-fra
|
| 1088 |
+
dataset:
|
| 1089 |
+
name: tico19-test
|
| 1090 |
+
type: tico19-test
|
| 1091 |
+
args: pus-fra
|
| 1092 |
+
metrics:
|
| 1093 |
+
- name: BLEU
|
| 1094 |
+
type: bleu
|
| 1095 |
+
value: 19.2
|
| 1096 |
+
- name: chr-F
|
| 1097 |
+
type: chrf
|
| 1098 |
+
value: 0.46091
|
| 1099 |
+
- task:
|
| 1100 |
+
name: Translation pus-por
|
| 1101 |
+
type: translation
|
| 1102 |
+
args: pus-por
|
| 1103 |
+
dataset:
|
| 1104 |
+
name: tico19-test
|
| 1105 |
+
type: tico19-test
|
| 1106 |
+
args: pus-por
|
| 1107 |
+
metrics:
|
| 1108 |
+
- name: BLEU
|
| 1109 |
+
type: bleu
|
| 1110 |
+
value: 24.1
|
| 1111 |
+
- name: chr-F
|
| 1112 |
+
type: chrf
|
| 1113 |
+
value: 0.51033
|
| 1114 |
+
- task:
|
| 1115 |
+
name: Translation pus-spa
|
| 1116 |
+
type: translation
|
| 1117 |
+
args: pus-spa
|
| 1118 |
+
dataset:
|
| 1119 |
+
name: tico19-test
|
| 1120 |
+
type: tico19-test
|
| 1121 |
+
args: pus-spa
|
| 1122 |
+
metrics:
|
| 1123 |
+
- name: BLEU
|
| 1124 |
+
type: bleu
|
| 1125 |
+
value: 25.9
|
| 1126 |
+
- name: chr-F
|
| 1127 |
+
type: chrf
|
| 1128 |
+
value: 0.51857
|
| 1129 |
+
- task:
|
| 1130 |
+
name: Translation pus-eng
|
| 1131 |
+
type: translation
|
| 1132 |
+
args: pus-eng
|
| 1133 |
+
dataset:
|
| 1134 |
+
name: newstest2020
|
| 1135 |
+
type: wmt-2020-news
|
| 1136 |
+
args: pus-eng
|
| 1137 |
+
metrics:
|
| 1138 |
+
- name: BLEU
|
| 1139 |
+
type: bleu
|
| 1140 |
+
value: 13.1
|
| 1141 |
+
- name: chr-F
|
| 1142 |
+
type: chrf
|
| 1143 |
+
value: 0.37487
|
| 1144 |
+
---
|
| 1145 |
+
# opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa
|
| 1146 |
+
|
| 1147 |
+
## Table of Contents
|
| 1148 |
+
- [Model Details](#model-details)
|
| 1149 |
+
- [Uses](#uses)
|
| 1150 |
+
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
|
| 1151 |
+
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
|
| 1152 |
+
- [Training](#training)
|
| 1153 |
+
- [Evaluation](#evaluation)
|
| 1154 |
+
- [Citation Information](#citation-information)
|
| 1155 |
+
- [Acknowledgements](#acknowledgements)
|
| 1156 |
+
|
| 1157 |
+
## Model Details
|
| 1158 |
+
|
| 1159 |
+
Neural machine translation model for translating from Iranian languages (ira) to unknown (deu+eng+fra+por+spa).
|
| 1160 |
+
|
| 1161 |
+
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).
|
| 1162 |
+
**Model Description:**
|
| 1163 |
+
- **Developed by:** Language Technology Research Group at the University of Helsinki
|
| 1164 |
+
- **Model Type:** Translation (transformer-big)
|
| 1165 |
+
- **Release**: 2024-05-30
|
| 1166 |
+
- **License:** Apache-2.0
|
| 1167 |
+
- **Language(s):**
|
| 1168 |
+
- Source Language(s): bal ckb diq fas glk jdt kmr kur lrc mzn oss pal pes prs pus sdh tgk tly zza
|
| 1169 |
+
- Target Language(s): deu eng fra por spa
|
| 1170 |
+
- Valid Target Language Labels: >>deu<< >>eng<< >>fra<< >>por<< >>spa<< >>xxx<<
|
| 1171 |
+
- **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ira-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
|
| 1172 |
+
- **Resources for more information:**
|
| 1173 |
+
- [OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/ira-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
|
| 1174 |
+
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
|
| 1175 |
+
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
|
| 1176 |
+
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/)
|
| 1177 |
+
- [HPLT bilingual data v1 (as part of the Tatoeba Translation Challenge dataset)](https://hplt-project.org/datasets/v1)
|
| 1178 |
+
- [A massively parallel Bible corpus](https://aclanthology.org/L14-1215/)
|
| 1179 |
+
|
| 1180 |
+
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. `>>deu<<`
|
| 1181 |
+
|
| 1182 |
+
## Uses
|
| 1183 |
+
|
| 1184 |
+
This model can be used for translation and text-to-text generation.
|
| 1185 |
+
|
| 1186 |
+
## Risks, Limitations and Biases
|
| 1187 |
+
|
| 1188 |
+
**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.**
|
| 1189 |
+
|
| 1190 |
+
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)).
|
| 1191 |
+
|
| 1192 |
+
## How to Get Started With the Model
|
| 1193 |
+
|
| 1194 |
+
A short example code:
|
| 1195 |
+
|
| 1196 |
+
```python
|
| 1197 |
+
from transformers import MarianMTModel, MarianTokenizer
|
| 1198 |
+
|
| 1199 |
+
src_text = [
|
| 1200 |
+
">>deu<< Replace this with text in an accepted source language.",
|
| 1201 |
+
">>spa<< This is the second sentence."
|
| 1202 |
+
]
|
| 1203 |
+
|
| 1204 |
+
model_name = "pytorch-models/opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa"
|
| 1205 |
+
tokenizer = MarianTokenizer.from_pretrained(model_name)
|
| 1206 |
+
model = MarianMTModel.from_pretrained(model_name)
|
| 1207 |
+
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
|
| 1208 |
+
|
| 1209 |
+
for t in translated:
|
| 1210 |
+
print( tokenizer.decode(t, skip_special_tokens=True) )
|
| 1211 |
+
```
|
| 1212 |
+
|
| 1213 |
+
You can also use OPUS-MT models with the transformers pipelines, for example:
|
| 1214 |
+
|
| 1215 |
+
```python
|
| 1216 |
+
from transformers import pipeline
|
| 1217 |
+
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa")
|
| 1218 |
+
print(pipe(">>deu<< Replace this with text in an accepted source language."))
|
| 1219 |
+
```
|
| 1220 |
+
|
| 1221 |
+
## Training
|
| 1222 |
+
|
| 1223 |
+
- **Data**: opusTCv20230926max50+bt+jhubc ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
|
| 1224 |
+
- **Pre-processing**: SentencePiece (spm32k,spm32k)
|
| 1225 |
+
- **Model Type:** transformer-big
|
| 1226 |
+
- **Original MarianNMT Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ira-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
|
| 1227 |
+
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
|
| 1228 |
+
|
| 1229 |
+
## Evaluation
|
| 1230 |
+
|
| 1231 |
+
* [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/ira-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
|
| 1232 |
+
* test set translations: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ira-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt)
|
| 1233 |
+
* test set scores: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ira-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt)
|
| 1234 |
+
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
|
| 1235 |
+
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
|
| 1236 |
+
|
| 1237 |
+
| langpair | testset | chr-F | BLEU | #sent | #words |
|
| 1238 |
+
|----------|---------|-------|-------|-------|--------|
|
| 1239 |
+
| fas-deu | tatoeba-test-v2021-08-07 | 0.59737 | 36.1 | 3185 | 25590 |
|
| 1240 |
+
| fas-eng | tatoeba-test-v2021-08-07 | 0.59871 | 35.8 | 3762 | 31480 |
|
| 1241 |
+
| fas-fra | tatoeba-test-v2021-08-07 | 0.58095 | 36.3 | 376 | 3377 |
|
| 1242 |
+
| kur_Latn-deu | tatoeba-test-v2021-08-07 | 0.40276 | 24.9 | 223 | 1323 |
|
| 1243 |
+
| pes-eng | tatoeba-test-v2021-08-07 | 0.60717 | 42.3 | 3757 | 31411 |
|
| 1244 |
+
| ckb-deu | flores101-devtest | 0.40117 | 11.6 | 1012 | 25094 |
|
| 1245 |
+
| ckb-eng | flores101-devtest | 0.48321 | 21.6 | 1012 | 24721 |
|
| 1246 |
+
| ckb-fra | flores101-devtest | 0.44260 | 17.2 | 1012 | 28343 |
|
| 1247 |
+
| ckb-por | flores101-devtest | 0.43179 | 16.2 | 1012 | 26519 |
|
| 1248 |
+
| fas-eng | flores101-devtest | 0.61134 | 34.4 | 1012 | 24721 |
|
| 1249 |
+
| pus-eng | flores101-devtest | 0.49556 | 22.7 | 1012 | 24721 |
|
| 1250 |
+
| pus-fra | flores101-devtest | 0.45248 | 17.8 | 1012 | 28343 |
|
| 1251 |
+
| tgk-eng | flores101-devtest | 0.53630 | 25.4 | 1012 | 24721 |
|
| 1252 |
+
| tgk-fra | flores101-devtest | 0.49084 | 21.0 | 1012 | 28343 |
|
| 1253 |
+
| tgk-spa | flores101-devtest | 0.43524 | 15.5 | 1012 | 29199 |
|
| 1254 |
+
| ckb-deu | flores200-devtest | 0.40369 | 11.7 | 1012 | 25094 |
|
| 1255 |
+
| ckb-eng | flores200-devtest | 0.48447 | 21.5 | 1012 | 24721 |
|
| 1256 |
+
| ckb-fra | flores200-devtest | 0.44026 | 17.1 | 1012 | 28343 |
|
| 1257 |
+
| ckb-por | flores200-devtest | 0.43192 | 16.4 | 1012 | 26519 |
|
| 1258 |
+
| pes-deu | flores200-devtest | 0.51542 | 21.5 | 1012 | 25094 |
|
| 1259 |
+
| pes-eng | flores200-devtest | 0.61372 | 34.9 | 1012 | 24721 |
|
| 1260 |
+
| pes-fra | flores200-devtest | 0.56347 | 29.2 | 1012 | 28343 |
|
| 1261 |
+
| pes-por | flores200-devtest | 0.55676 | 28.5 | 1012 | 26519 |
|
| 1262 |
+
| pes-spa | flores200-devtest | 0.48334 | 19.8 | 1012 | 29199 |
|
| 1263 |
+
| prs-deu | flores200-devtest | 0.50562 | 21.2 | 1012 | 25094 |
|
| 1264 |
+
| prs-eng | flores200-devtest | 0.60716 | 35.1 | 1012 | 24721 |
|
| 1265 |
+
| prs-fra | flores200-devtest | 0.54769 | 27.8 | 1012 | 28343 |
|
| 1266 |
+
| prs-por | flores200-devtest | 0.54073 | 27.2 | 1012 | 26519 |
|
| 1267 |
+
| prs-spa | flores200-devtest | 0.46850 | 18.6 | 1012 | 29199 |
|
| 1268 |
+
| tgk-deu | flores200-devtest | 0.43115 | 14.2 | 1012 | 25094 |
|
| 1269 |
+
| tgk-eng | flores200-devtest | 0.53705 | 25.6 | 1012 | 24721 |
|
| 1270 |
+
| tgk-fra | flores200-devtest | 0.48902 | 20.7 | 1012 | 28343 |
|
| 1271 |
+
| tgk-por | flores200-devtest | 0.48519 | 20.7 | 1012 | 26519 |
|
| 1272 |
+
| tgk-spa | flores200-devtest | 0.43563 | 15.7 | 1012 | 29199 |
|
| 1273 |
+
| fas-deu | ntrex128 | 0.47408 | 16.7 | 1997 | 48761 |
|
| 1274 |
+
| fas-eng | ntrex128 | 0.55350 | 26.4 | 1997 | 47673 |
|
| 1275 |
+
| fas-fra | ntrex128 | 0.50311 | 22.1 | 1997 | 53481 |
|
| 1276 |
+
| fas-por | ntrex128 | 0.48005 | 19.1 | 1997 | 51631 |
|
| 1277 |
+
| fas-spa | ntrex128 | 0.50973 | 23.6 | 1997 | 54107 |
|
| 1278 |
+
| prs-deu | ntrex128 | 0.45191 | 14.9 | 1997 | 48761 |
|
| 1279 |
+
| prs-eng | ntrex128 | 0.54761 | 26.6 | 1997 | 47673 |
|
| 1280 |
+
| prs-fra | ntrex128 | 0.47819 | 19.9 | 1997 | 53481 |
|
| 1281 |
+
| prs-por | ntrex128 | 0.46241 | 17.4 | 1997 | 51631 |
|
| 1282 |
+
| prs-spa | ntrex128 | 0.48712 | 21.4 | 1997 | 54107 |
|
| 1283 |
+
| pus-eng | ntrex128 | 0.43901 | 17.4 | 1997 | 47673 |
|
| 1284 |
+
| pus-spa | ntrex128 | 0.40812 | 14.1 | 1997 | 54107 |
|
| 1285 |
+
| tgk_Cyrl-eng | ntrex128 | 0.46839 | 18.6 | 1997 | 47673 |
|
| 1286 |
+
| tgk_Cyrl-fra | ntrex128 | 0.42569 | 15.1 | 1997 | 53481 |
|
| 1287 |
+
| tgk_Cyrl-por | ntrex128 | 0.41632 | 13.7 | 1997 | 51631 |
|
| 1288 |
+
| tgk_Cyrl-spa | ntrex128 | 0.43763 | 16.8 | 1997 | 54107 |
|
| 1289 |
+
| ckb-eng | tico19-test | 0.61905 | 40.1 | 2100 | 56315 |
|
| 1290 |
+
| ckb-fra | tico19-test | 0.45070 | 19.7 | 2100 | 64661 |
|
| 1291 |
+
| ckb-por | tico19-test | 0.49617 | 22.9 | 2100 | 62729 |
|
| 1292 |
+
| ckb-spa | tico19-test | 0.50543 | 24.9 | 2100 | 66563 |
|
| 1293 |
+
| fas-eng | tico19-test | 0.64016 | 37.3 | 2100 | 56315 |
|
| 1294 |
+
| fas-fra | tico19-test | 0.53319 | 26.1 | 2100 | 64661 |
|
| 1295 |
+
| fas-por | tico19-test | 0.58008 | 30.6 | 2100 | 62729 |
|
| 1296 |
+
| fas-spa | tico19-test | 0.59239 | 33.3 | 2100 | 66563 |
|
| 1297 |
+
| prs-eng | tico19-test | 0.61702 | 34.8 | 2100 | 56824 |
|
| 1298 |
+
| prs-fra | tico19-test | 0.51218 | 24.0 | 2100 | 64661 |
|
| 1299 |
+
| prs-por | tico19-test | 0.55888 | 28.6 | 2100 | 62729 |
|
| 1300 |
+
| prs-spa | tico19-test | 0.57494 | 31.1 | 2100 | 66563 |
|
| 1301 |
+
| pus-eng | tico19-test | 0.57586 | 32.1 | 2100 | 56315 |
|
| 1302 |
+
| pus-fra | tico19-test | 0.46091 | 19.2 | 2100 | 64661 |
|
| 1303 |
+
| pus-por | tico19-test | 0.51033 | 24.1 | 2100 | 62729 |
|
| 1304 |
+
| pus-spa | tico19-test | 0.51857 | 25.9 | 2100 | 66563 |
|
| 1305 |
+
|
| 1306 |
+
## Citation Information
|
| 1307 |
+
|
| 1308 |
+
* 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.)
|
| 1309 |
+
|
| 1310 |
+
```bibtex
|
| 1311 |
+
@article{tiedemann2023democratizing,
|
| 1312 |
+
title={Democratizing neural machine translation with {OPUS-MT}},
|
| 1313 |
+
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},
|
| 1314 |
+
journal={Language Resources and Evaluation},
|
| 1315 |
+
number={58},
|
| 1316 |
+
pages={713--755},
|
| 1317 |
+
year={2023},
|
| 1318 |
+
publisher={Springer Nature},
|
| 1319 |
+
issn={1574-0218},
|
| 1320 |
+
doi={10.1007/s10579-023-09704-w}
|
| 1321 |
+
}
|
| 1322 |
+
|
| 1323 |
+
@inproceedings{tiedemann-thottingal-2020-opus,
|
| 1324 |
+
title = "{OPUS}-{MT} {--} Building open translation services for the World",
|
| 1325 |
+
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
|
| 1326 |
+
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
|
| 1327 |
+
month = nov,
|
| 1328 |
+
year = "2020",
|
| 1329 |
+
address = "Lisboa, Portugal",
|
| 1330 |
+
publisher = "European Association for Machine Translation",
|
| 1331 |
+
url = "https://aclanthology.org/2020.eamt-1.61",
|
| 1332 |
+
pages = "479--480",
|
| 1333 |
+
}
|
| 1334 |
+
|
| 1335 |
+
@inproceedings{tiedemann-2020-tatoeba,
|
| 1336 |
+
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
|
| 1337 |
+
author = {Tiedemann, J{\"o}rg},
|
| 1338 |
+
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
|
| 1339 |
+
month = nov,
|
| 1340 |
+
year = "2020",
|
| 1341 |
+
address = "Online",
|
| 1342 |
+
publisher = "Association for Computational Linguistics",
|
| 1343 |
+
url = "https://aclanthology.org/2020.wmt-1.139",
|
| 1344 |
+
pages = "1174--1182",
|
| 1345 |
+
}
|
| 1346 |
+
```
|
| 1347 |
+
|
| 1348 |
+
## Acknowledgements
|
| 1349 |
+
|
| 1350 |
+
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/).
|
| 1351 |
+
|
| 1352 |
+
## Model conversion info
|
| 1353 |
+
|
| 1354 |
+
* transformers version: 4.45.1
|
| 1355 |
+
* OPUS-MT git hash: 0882077
|
| 1356 |
+
* port time: Tue Oct 8 11:54:09 EEST 2024
|
| 1357 |
+
* port machine: LM0-400-22516.local
|
benchmark_results.txt
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
multi-multi tatoeba-test-v2020-07-28-v2023-09-26 0.56042 34.0 8920 71316
|
| 2 |
+
ckb-deu flores101-devtest 0.40117 11.6 1012 25094
|
| 3 |
+
ckb-eng flores101-devtest 0.48321 21.6 1012 24721
|
| 4 |
+
ckb-fra flores101-devtest 0.44260 17.2 1012 28343
|
| 5 |
+
ckb-por flores101-devtest 0.43179 16.2 1012 26519
|
| 6 |
+
fas-eng flores101-devtest 0.61134 34.4 1012 24721
|
| 7 |
+
pus-eng flores101-devtest 0.49556 22.7 1012 24721
|
| 8 |
+
pus-fra flores101-devtest 0.45248 17.8 1012 28343
|
| 9 |
+
tgk-eng flores101-devtest 0.53630 25.4 1012 24721
|
| 10 |
+
tgk-fra flores101-devtest 0.49084 21.0 1012 28343
|
| 11 |
+
tgk-spa flores101-devtest 0.43524 15.5 1012 29199
|
| 12 |
+
ckb-deu flores200-devtest 0.40369 11.7 1012 25094
|
| 13 |
+
ckb-eng flores200-devtest 0.48447 21.5 1012 24721
|
| 14 |
+
ckb-fra flores200-devtest 0.44026 17.1 1012 28343
|
| 15 |
+
ckb-por flores200-devtest 0.43192 16.4 1012 26519
|
| 16 |
+
ckb-spa flores200-devtest 0.38880 11.7 1012 29199
|
| 17 |
+
kmr-deu flores200-devtest 0.32168 6.7 1012 25094
|
| 18 |
+
kmr-eng flores200-devtest 0.37372 12.4 1012 24721
|
| 19 |
+
kmr-fra flores200-devtest 0.33796 8.6 1012 28343
|
| 20 |
+
kmr-por flores200-devtest 0.33604 9.6 1012 26519
|
| 21 |
+
kmr-spa flores200-devtest 0.32062 7.7 1012 29199
|
| 22 |
+
pes-deu flores200-devtest 0.51542 21.5 1012 25094
|
| 23 |
+
pes-eng flores200-devtest 0.61372 34.9 1012 24721
|
| 24 |
+
pes-fra flores200-devtest 0.56347 29.2 1012 28343
|
| 25 |
+
pes-por flores200-devtest 0.55676 28.5 1012 26519
|
| 26 |
+
pes-spa flores200-devtest 0.48334 19.8 1012 29199
|
| 27 |
+
prs-deu flores200-devtest 0.50562 21.2 1012 25094
|
| 28 |
+
prs-eng flores200-devtest 0.60716 35.1 1012 24721
|
| 29 |
+
prs-fra flores200-devtest 0.54769 27.8 1012 28343
|
| 30 |
+
prs-por flores200-devtest 0.54073 27.2 1012 26519
|
| 31 |
+
prs-spa flores200-devtest 0.46850 18.6 1012 29199
|
| 32 |
+
tgk-deu flores200-devtest 0.43115 14.2 1012 25094
|
| 33 |
+
tgk-eng flores200-devtest 0.53705 25.6 1012 24721
|
| 34 |
+
tgk-fra flores200-devtest 0.48902 20.7 1012 28343
|
| 35 |
+
tgk-por flores200-devtest 0.48519 20.7 1012 26519
|
| 36 |
+
tgk-spa flores200-devtest 0.43563 15.7 1012 29199
|
| 37 |
+
pus-eng newstest2020 0.37487 13.1 2719 53382
|
| 38 |
+
fas-deu ntrex128 0.47408 16.7 1997 48761
|
| 39 |
+
fas-eng ntrex128 0.55350 26.4 1997 47673
|
| 40 |
+
fas-fra ntrex128 0.50311 22.1 1997 53481
|
| 41 |
+
fas-por ntrex128 0.48005 19.1 1997 51631
|
| 42 |
+
fas-spa ntrex128 0.50973 23.6 1997 54107
|
| 43 |
+
kmr-deu ntrex128 0.32165 6.8 1997 48761
|
| 44 |
+
kmr-eng ntrex128 0.38189 12.8 1997 47673
|
| 45 |
+
kmr-fra ntrex128 0.34023 9.6 1997 53481
|
| 46 |
+
kmr-por ntrex128 0.33306 8.6 1997 51631
|
| 47 |
+
kmr-spa ntrex128 0.000 0.0 1997 0
|
| 48 |
+
prs-deu ntrex128 0.45191 14.9 1997 48761
|
| 49 |
+
prs-eng ntrex128 0.54761 26.6 1997 47673
|
| 50 |
+
prs-fra ntrex128 0.47819 19.9 1997 53481
|
| 51 |
+
prs-por ntrex128 0.46241 17.4 1997 51631
|
| 52 |
+
prs-spa ntrex128 0.48712 21.4 1997 54107
|
| 53 |
+
pus-deu ntrex128 0.38295 9.8 1997 48761
|
| 54 |
+
pus-eng ntrex128 0.43901 17.4 1997 47673
|
| 55 |
+
pus-fra ntrex128 0.39661 12.4 1997 53481
|
| 56 |
+
pus-por ntrex128 0.38694 11.4 1997 51631
|
| 57 |
+
pus-spa ntrex128 0.40812 14.1 1997 54107
|
| 58 |
+
tgk_Cyrl-deu ntrex128 0.38740 10.7 1997 48761
|
| 59 |
+
tgk_Cyrl-eng ntrex128 0.46839 18.6 1997 47673
|
| 60 |
+
tgk_Cyrl-fra ntrex128 0.42569 15.1 1997 53481
|
| 61 |
+
tgk_Cyrl-por ntrex128 0.41632 13.7 1997 51631
|
| 62 |
+
tgk_Cyrl-spa ntrex128 0.43763 16.8 1997 54107
|
| 63 |
+
zza-eng tatoeba-test-v2020-07-28 0.12456 0.9 523 3120
|
| 64 |
+
fas-fra tatoeba-test-v2021-03-30 0.58236 36.6 383 3442
|
| 65 |
+
pes-eng tatoeba-test-v2021-03-30 0.60756 42.8 3763 31439
|
| 66 |
+
zza-eng tatoeba-test-v2021-03-30 0.12511 0.9 533 3182
|
| 67 |
+
fas-deu tatoeba-test-v2021-08-07 0.59737 36.1 3185 25590
|
| 68 |
+
fas-eng tatoeba-test-v2021-08-07 0.59871 35.8 3762 31480
|
| 69 |
+
fas-fra tatoeba-test-v2021-08-07 0.58095 36.3 376 3377
|
| 70 |
+
kur_Latn-deu tatoeba-test-v2021-08-07 0.40276 24.9 223 1323
|
| 71 |
+
kur_Latn-eng tatoeba-test-v2021-08-07 0.000 0.0 290 0
|
| 72 |
+
pes-eng tatoeba-test-v2021-08-07 0.60717 42.3 3757 31411
|
| 73 |
+
zza-eng tatoeba-test-v2021-08-07 0.12989 1.4 529 3162
|
| 74 |
+
ckb-eng tico19-test 0.61905 40.1 2100 56315
|
| 75 |
+
ckb-fra tico19-test 0.45070 19.7 2100 64661
|
| 76 |
+
ckb-por tico19-test 0.49617 22.9 2100 62729
|
| 77 |
+
ckb-spa tico19-test 0.50543 24.9 2100 66563
|
| 78 |
+
fas-eng tico19-test 0.64016 37.3 2100 56315
|
| 79 |
+
fas-fra tico19-test 0.53319 26.1 2100 64661
|
| 80 |
+
fas-por tico19-test 0.58008 30.6 2100 62729
|
| 81 |
+
fas-spa tico19-test 0.59239 33.3 2100 66563
|
| 82 |
+
prs-eng tico19-test 0.61702 34.8 2100 56824
|
| 83 |
+
prs-fra tico19-test 0.51218 24.0 2100 64661
|
| 84 |
+
prs-por tico19-test 0.55888 28.6 2100 62729
|
| 85 |
+
prs-spa tico19-test 0.57494 31.1 2100 66563
|
| 86 |
+
pus-eng tico19-test 0.57586 32.1 2100 56315
|
| 87 |
+
pus-fra tico19-test 0.46091 19.2 2100 64661
|
| 88 |
+
pus-por tico19-test 0.51033 24.1 2100 62729
|
| 89 |
+
pus-spa tico19-test 0.51857 25.9 2100 66563
|
benchmark_translations.zip
ADDED
|
File without changes
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pytorch-models/opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MarianMTModel"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 1024,
|
| 12 |
+
"decoder_attention_heads": 16,
|
| 13 |
+
"decoder_ffn_dim": 4096,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 60955,
|
| 17 |
+
"decoder_vocab_size": 60956,
|
| 18 |
+
"dropout": 0.1,
|
| 19 |
+
"encoder_attention_heads": 16,
|
| 20 |
+
"encoder_ffn_dim": 4096,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 6,
|
| 23 |
+
"eos_token_id": 502,
|
| 24 |
+
"forced_eos_token_id": null,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"max_length": null,
|
| 28 |
+
"max_position_embeddings": 1024,
|
| 29 |
+
"model_type": "marian",
|
| 30 |
+
"normalize_embedding": false,
|
| 31 |
+
"num_beams": null,
|
| 32 |
+
"num_hidden_layers": 6,
|
| 33 |
+
"pad_token_id": 60955,
|
| 34 |
+
"scale_embedding": true,
|
| 35 |
+
"share_encoder_decoder_embeddings": true,
|
| 36 |
+
"static_position_embeddings": true,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.45.1",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 60956
|
| 41 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bad_words_ids": [
|
| 4 |
+
[
|
| 5 |
+
60955
|
| 6 |
+
]
|
| 7 |
+
],
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"decoder_start_token_id": 60955,
|
| 10 |
+
"eos_token_id": 502,
|
| 11 |
+
"forced_eos_token_id": 502,
|
| 12 |
+
"max_length": 512,
|
| 13 |
+
"num_beams": 4,
|
| 14 |
+
"pad_token_id": 60955,
|
| 15 |
+
"transformers_version": "4.45.1"
|
| 16 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c117d5020ee76ac9dc8a996fcc9ab44e4210691a6f5b83674f752dfa761324c9
|
| 3 |
+
size 955378720
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:767745f4e5c174d2c27fb50d75640a289794b2c053825a4ccf77d439133c58df
|
| 3 |
+
size 955429957
|
source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:467f88a72be71e523bca01c4ffd970d3466ff3d405b91c6e12f607570ed06dba
|
| 3 |
+
size 885588
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac3b523a6d0e93e46954b126e38bc2fbb9dd285fb312c3fdc8b319fddc3d299a
|
| 3 |
+
size 803985
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"source_lang": "ira", "target_lang": "deu+eng+fra+por+spa", "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_2024-05-30/ira-deu+eng+fra+por+spa", "tokenizer_class": "MarianTokenizer"}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|