Instructions to use Helsinki-NLP/opus-mt-ROMANCE-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-ROMANCE-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-ROMANCE-en")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-ROMANCE-en") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-ROMANCE-en") - Inference
- Notebooks
- Google Colab
- Kaggle
Why does translating a single word sometimes return multiple of the same value?
#3
by wheatbun - opened
I'm trying to translate a single Portuguese word, "Muito" to English. The ROMANCE-en model returns:
Very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very...
How can I return "Very"?
Also, in a similar problem, inputting "." returns:
- No, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no.