Translation
Transformers
PyTorch
TensorFlow
Safetensors
Hungarian
Ukrainian
marian
text2text-generation
opus-mt-tc
Eval Results (legacy)
Instructions to use Helsinki-NLP/opus-mt-tc-base-uk-hu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-tc-base-uk-hu 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-base-uk-hu")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-tc-base-uk-hu") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-tc-base-uk-hu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| ukr-hun flores101-devtest 0.51953 20.2 1012 22183 | |
| ukr-hun flores101-dev 0.52022 21.2 997 21222 | |
| ukr-hun tatoeba-test-v2020-07-28 0.67495 43.9 464 2433 | |
| ukr-hun tatoeba-test-v2021-03-30 0.67383 43.8 474 2492 | |
| ukr-hun tatoeba-test-v2021-08-07 0.67544 44.0 473 2472 | |