Instructions to use Helsinki-NLP/opus-mt-ru-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-ru-en 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-ru-en")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-ru-en") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-ru-en") - Inference
- Notebooks
- Google Colab
- Kaggle
The model translates letters incorrectly.
#3
by ierhon - opened
I write "а б в г д" and it responds "(a) In per cent of the total gross domestic product (GDP)" which is obviously incorrect (correct would be "a b c d e" or "a b v g d"). Same with any random letters. That's a problem with training.
Но если ввести "абвгд", то ответ будет таким "abvd". А если ввести "а, б, в, г, д", то такой "a, b, g, d". Согласен все ещё не очень, но лучше.
But if you enter "абвгд", then the answer will be "abvd". And if you enter "а, б, в, г, д", then such "a, b, g, d". Still not great, but better.
