opus-mt-da-no Open-source Machine Translation Model - Free and Accurate Translation from Danish to Norwegian

Opus Mt Da No

Developed by Helsinki-NLP

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

Machine Translation

Transformers

OtherOpen Source License:Apache-2.0 #Danish-Norwegian translation #Multi-dialect support #High BLEU score

Downloads 31

Release Time : 3/2/2022

Model Overview

This model is specifically designed for Danish to Norwegian translation tasks, employing standardized preprocessing and SentencePiece tokenization technology, supporting output in two Norwegian variants.

Model Features

Multi-dialect support

Supports output in both Bokmål (nob) and Nynorsk (nno) Norwegian dialect variants

Efficient tokenization

Uses SentencePiece tokenization technology (spm12k) for preprocessing

High-precision translation

Achieves high scores of 66.4 BLEU and 0.801 chr-F on the Tatoeba test set

Model Capabilities

Danish to Norwegian text translation

Support for dialect selection output

Batch text processing

Use Cases

Language services

Document translation

Translate Danish documents into Norwegian official documents

Maintains accuracy of professional terminology and fluency of sentence structure

Cross-language communication

Real-time translation of conversations between Danish and Norwegian speakers

Enables barrier-free communication in the Scandinavian region

🚀 dan-nor Translation Model

This project focuses on the translation between Danish and Norwegian. It provides a specific model and related evaluation metrics, facilitating the research and application of Danish - Norwegian translation.

🚀 Quick Start

The dan - nor model is designed for Danish - Norwegian translation. Here are some key details:

Source Group: Danish
Target Group: Norwegian
OPUS Readme: dan-nor
Model: transformer-align
Source Language(s): dan
Target Language(s): nno, nob
Pre - processing: normalization + SentencePiece (spm12k,spm12k)
A sentence initial language token is required in the form of >>id<< (id = valid target language ID)
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

📚 Documentation

Benchmarks

Testset	BLEU	chr - F
Tatoeba - test.dan.nor	66.4	0.801

System Info

Property	Details
hf_name	dan - nor
source_languages	dan
target_languages	nor
opus_readme_url	https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/dan-nor/README.md
original_repo	Tatoeba - Challenge
tags	['translation']
languages	['da', 'no']
src_constituents	{'dan'}
tgt_constituents	{'nob', 'nno'}
src_multilingual	False
tgt_multilingual	False
prepro	normalization + SentencePiece (spm12k,spm12k)
url_model	https://object.pouta.csc.fi/Tatoeba-MT-models/dan-nor/opus-2020-06-17.zip
url_test_set	https://object.pouta.csc.fi/Tatoeba-MT-models/dan-nor/opus-2020-06-17.test.txt
src_alpha3	dan
tgt_alpha3	nor
short_pair	da - no
chrF2_score	0.8009999999999999
bleu	66.4
brevity_penalty	0.996
ref_len	9691.0
src_name	Danish
tgt_name	Norwegian
train_date	2020 - 06 - 17
src_alpha2	da
tgt_alpha2	no
prefer_old	False
long_pair	dan - nor
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