Instructions to use Helsinki-NLP/opus-mt-NORTH_EU-NORTH_EU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-NORTH_EU-NORTH_EU 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-NORTH_EU-NORTH_EU")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-NORTH_EU-NORTH_EU") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-NORTH_EU-NORTH_EU") - Notebooks
- Google Colab
- Kaggle
opus-mt-NORTH_EU-NORTH_EU
source languages: de,nl,fy,af,da,fo,is,no,nb,nn,sv
target languages: de,nl,fy,af,da,fo,is,no,nb,nn,sv
OPUS readme: de+nl+fy+af+da+fo+is+no+nb+nn+sv-de+nl+fy+af+da+fo+is+no+nb+nn+sv
dataset: opus
model: transformer-align
pre-processing: normalization + SentencePiece
a sentence initial language token is required in the form of
>>id<<(id = valid target language ID)download original weights: opus-2020-01-15.zip
test set translations: opus-2020-01-15.test.txt
test set scores: opus-2020-01-15.eval.txt
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| Tatoeba.de.sv | 48.1 | 0.663 |
- Downloads last month
- 38