Opus-mt-no-da Open-source Machine Translation Model - Free and Efficient Translation from Norwegian to Danish

Opus Mt No Da

Developed by Helsinki-NLP

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

Machine Translation

Transformers

OtherOpen Source License:Apache-2.0 #Nordic language translation #High-precision translation #SentencePiece tokenization

Downloads 40

Release Time : 3/2/2022

Model Overview

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

Model Features

Multi-dialect Support

Supports translation from both Bokmål (nob) and Nynorsk (nno) Norwegian variants to Danish

High-performance Translation

Achieves high-quality translation results with 65.0 BLEU and 0.792 chr-F scores on the Tatoeba test set

Standardized Preprocessing

Employs standardized preprocessing and SentencePiece tokenization (spm12k) to enhance translation quality

Model Capabilities

Norwegian to Danish text translation

Bokmål translation

Nynorsk translation

Use Cases

Language Translation

Daily Conversation Translation

Translate everyday Norwegian conversations into Danish

High-quality translation results (BLEU 65.0)

Document Translation

Translate Norwegian documents into Danish versions

🚀 Nor - Dan Translation Model

This project focuses on the translation between Norwegian and Danish, providing a reliable translation model and related evaluation data.

🚀 Quick Start

This model is used for Norwegian - Danish translation. You can download the original weights and test set translations through the provided links for evaluation and usage.

✨ Features

Translation Direction: Translates from Norwegian to Danish.
Model Type: transformer - align
Pre - processing: Normalization + SentencePiece (spm12k,spm12k)

📦 Installation

The installation steps are not provided in the original document. If you want to use this model, you can download the original weights from the following link: opus - 2020 - 06 - 17.zip

📚 Documentation

nor - dan

Source Group: Norwegian
Target Group: Danish
OPUS Readme: nor - dan

System Info

Property	Details
hf_name	nor - dan
source_languages	nor
target_languages	dan
opus_readme_url	https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/nor-dan/README.md
original_repo	Tatoeba - Challenge
tags	['translation']
languages	['no', 'da']
src_constituents	{'nob', 'nno'}
tgt_constituents	{'dan'}
src_multilingual	False
tgt_multilingual	False
prepro	normalization + SentencePiece (spm12k,spm12k)
url_model	https://object.pouta.csc.fi/Tatoeba-MT-models/nor-dan/opus-2020-06-17.zip
url_test_set	https://object.pouta.csc.fi/Tatoeba-MT-models/nor-dan/opus-2020-06-17.test.txt
src_alpha3	nor
tgt_alpha3	dan
short_pair	no - da
chrF2_score	0.792
bleu	65.0
brevity_penalty	0.995
ref_len	9865.0
src_name	Norwegian
tgt_name	Danish
train_date	2020 - 06 - 17
src_alpha2	no
tgt_alpha2	da
prefer_old	False
long_pair	nor - dan
helsinki_git_sha	480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
transformers_git_sha	2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
port_machine	brutasse
port_time	2020 - 08 - 21 - 14:41

🔧 Technical Details

Benchmarks

testset	BLEU	chr - F
Tatoeba - test.nor.dan	65.0	0.792

📄 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