Translation
Transformers
PyTorch
Safetensors
marian
text2text-generation
opus-mt-tc
Eval Results (legacy)
Instructions to use Helsinki-NLP/opus-mt-tc-big-zle-de with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-tc-big-zle-de 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="Helsinki-NLP/opus-mt-tc-big-zle-de")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-tc-big-zle-de") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-tc-big-zle-de", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| bel-deu flores101-dev 0.46864 12.9 997 24097 | |
| rus-deu flores101-dev 0.56335 26.6 997 24097 | |
| bel-deu flores101-devtest 0.47052 12.9 1012 25094 | |
| rus-deu flores101-devtest 0.56159 26.1 1012 25094 | |
| ukr-deu flores101-devtest 0.57251 28.1 1012 25094 | |
| ukr-deu flores101-dev 0.56286 27.7 997 24097 | |
| rus-deu newstest2012 0.49257 19.8 3003 72886 | |
| rus-deu newstest2013 0.54015 25.2 3000 63737 | |
| bel-deu tatoeba-test-v2020-07-28 0.63697 44.7 550 4175 | |
| rus-deu tatoeba-test-v2020-07-28 0.69789 52.1 10000 76302 | |
| ukr-deu tatoeba-test-v2020-07-28 0.70875 54.8 10000 62298 | |
| bel-deu tatoeba-test-v2021-03-30 0.63794 44.8 554 4203 | |
| rus-deu tatoeba-test-v2021-03-30 0.69829 51.9 11265 86251 | |
| ukr-deu tatoeba-test-v2021-03-30 0.70939 54.9 10174 63575 | |
| bel-deu tatoeba-test-v2021-08-07 0.63720 44.8 551 4182 | |
| rus-deu tatoeba-test-v2021-08-07 0.69768 51.8 12800 98842 | |
| ukr-deu tatoeba-test-v2021-08-07 0.70860 54.7 10319 64646 | |