Loading…
Loading…
Helsinki-NLP/opus-mt-fi_nb_no_nn_ru_sv_en-SAMIPart of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-fi_nb_no_nn_ru_sv_en-SAMI
Canonical copy: https://huggingface.co/WindyTranslate/translate-fi_nb_no_nn_ru_sv_en-SAMI
Translates Finnish / Norwegian Bokmål / Norwegian / Norwegian Nynorsk / Russian / Swedish / English → Saami (Northern Sami, Lule Sami).
No quality score is published in this repository. Current screening scores, where measured, are on the catalogue page linked above.
Deployment formats in this repository (subfolders):
| Variant | Description |
|---|---|
lora/ |
WindyStandard — production baseline. Transformers format for GPU inference. |
lora-ct2-int8/ |
WindyStandard · CPU INT8 — CTranslate2 INT8 quantization of WindyStandard for CPU inference. |
Transformers (PyTorch):
from transformers import MarianMTModel, MarianTokenizer
tokenizer = MarianTokenizer.from_pretrained("WindstormLabs/translate-fi_nb_no_nn_ru_sv_en-SAMI", subfolder="lora")
model = MarianMTModel.from_pretrained("WindstormLabs/translate-fi_nb_no_nn_ru_sv_en-SAMI", subfolder="lora")
CTranslate2 (fast CPU inference):
import ctranslate2
translator = ctranslate2.Translator("path/to/translate-fi_nb_no_nn_ru_sv_en-SAMI/lora-ct2-int8")
The Windy Word apps are built on this model family.
Weights derived from Helsinki-NLP/opus-mt-fi_nb_no_nn_ru_sv_en-SAMI (OPUS-MT, Helsinki-NLP, University of Helsinki), licensed Apache-2.0. Windy variants are released under the same licence.