Translation
Transformers
PyTorch
TensorFlow
Safetensors
Czech
Slovak
Ukrainian
marian
text2text-generation
opus-mt-tc
Eval Results (legacy)
Instructions to use Helsinki-NLP/opus-mt-tc-base-uk-ces_slk 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-ces_slk 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-ces_slk")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-tc-base-uk-ces_slk") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-tc-base-uk-ces_slk", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| ukr-ces flores101-devtest 0.51283 23.0 1012 22101 | |
| ukr-slk flores101-devtest 0.51043 22.1 1012 22543 | |
| ukr-ces flores101-dev 0.50743 22.3 997 21183 | |
| ukr-slk flores101-dev 0.50624 22.0 997 21796 | |
| ukr-ces tatoeba-test-v2020-07-28 0.70661 54.2 1787 8550 | |
| ukr-ces tatoeba-test-v2021-03-30 0.70661 54.2 1787 8550 | |
| ukr-ces tatoeba-test-v2021-08-07 0.70661 54.2 1787 8550 | |