# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-SCANDINAVIA-SCANDINAVIA")
model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-SCANDINAVIA-SCANDINAVIA")Quick Links
opus-mt-SCANDINAVIA-SCANDINAVIA
source languages: da,fo,is,no,nb,nn,sv
target languages: da,fo,is,no,nb,nn,sv
OPUS readme: da+fo+is+no+nb+nn+sv-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-2019-12-18.zip
test set translations: opus-2019-12-18.test.txt
test set scores: opus-2019-12-18.eval.txt
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| Tatoeba.da.sv | 69.2 | 0.811 |
- Downloads last month
- 22
# 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-SCANDINAVIA-SCANDINAVIA")