Opus-mt-no-sv Open Source Machine Translation Model - Achieve Precise Norwegian to Swedish Translation for Free

Opus Mt No Sv

Developed by Helsinki-NLP

This is a Norwegian to Swedish machine translation model based on the transformer-align architecture, supporting translation tasks from both Bokmål and Nynorsk Norwegian to Swedish.

Machine Translation

Transformers

OtherOpen Source License:Apache-2.0 #Nordic language translation #High BLEU score #SentencePiece preprocessing

Downloads 391

Release Time : 3/2/2022

Model Overview

This model is specifically designed for Norwegian (including Bokmål and Nynorsk) to Swedish translation tasks, employing standardized preprocessing and SentencePiece tokenization techniques.

Model Features

Multi-dialect support

Supports translation for both Bokmål (nob) and Nynorsk (nno) dialects of Norwegian.

High-quality translation

Achieves high scores of 63.7 BLEU and 0.773 chr-F on the Tatoeba test set.

Standardized preprocessing

Utilizes standardized preprocessing and SentencePiece tokenization (spm4k).

Model Capabilities

Norwegian to Swedish text translation

Bokmål translation

Nynorsk translation

Use Cases

Language services

Document translation

Translate Norwegian documents into Swedish

High-quality translation results, BLEU 63.7

Cross-language communication

Facilitate communication between Norwegian and Swedish speakers

🚀 Nor - Swe Translation Model

This is a translation model for converting Norwegian to Swedish, offering high - quality translation services with specific pre - processing and evaluation metrics.

✨ Features

Translation Direction: Translates from Norwegian to Swedish.
Model Type: Uses the transformer - align model.
Pre - processing: Applies normalization and SentencePiece (spm4k, spm4k).

📦 Installation

The original weights of the model can be downloaded from opus - 2020 - 06 - 17.zip.

📚 Documentation

nor - swe

Source Group: Norwegian
Target Group: Swedish
OPUS Readme: nor - swe
Model: transformer - align
Source Language(s): nno, nob
Target Language(s): swe
Pre - processing: normalization + SentencePiece (spm4k, spm4k)
Download Original Weights: opus - 2020 - 06 - 17.zip
Test Set Translations: opus - 2020 - 06 - 17.test.txt
Test Set Scores: opus - 2020 - 06 - 17.eval.txt

Benchmarks

testset	BLEU	chr - F
Tatoeba - test.nor.swe	63.7	0.773

System Info

Property	Details
hf_name	nor - swe
source_languages	nor
target_languages	swe
opus_readme_url	https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/nor-swe/README.md
original_repo	Tatoeba - Challenge
tags	['translation']
languages	['no', 'sv']
src_constituents	{'nob', 'nno'}
tgt_constituents	{'swe'}
src_multilingual	False
tgt_multilingual	False
prepro	normalization + SentencePiece (spm4k, spm4k)
url_model	https://object.pouta.csc.fi/Tatoeba-MT-models/nor-swe/opus-2020-06-17.zip
url_test_set	https://object.pouta.csc.fi/Tatoeba-MT-models/nor-swe/opus-2020-06-17.test.txt
src_alpha3	nor
tgt_alpha3	swe
short_pair	no - sv
chrF2_score	0.773
bleu	63.7
brevity_penalty	0.9670000000000001
ref_len	3672.0
src_name	Norwegian
tgt_name	Swedish
train_date	2020 - 06 - 17
src_alpha2	no
tgt_alpha2	sv
prefer_old	False
long_pair	nor - swe
helsinki_git_sha	480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
transformers_git_sha	2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
port_machine	brutasse
port_time	2020 - 08 - 21 - 14:41

📄 License

This project is licensed under the Apache - 2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご