Opus-MT De-No Open-Source Machine Translation Model - Freely Translate between German and Two Norwegian Language Variants

Opus Mt De No

Developed by Helsinki-NLP

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

Machine Translation

Transformers

Supports Multiple LanguagesOpen Source License:Apache-2.0 #Multi-dialect Norwegian support #Standardized preprocessing #SentencePiece tokenization

Downloads 36

Release Time : 3/2/2022

Model Overview

This model specializes in German-to-Norwegian translation tasks, employing standardized preprocessing and SentencePiece tokenization techniques, suitable for general text translation scenarios.

Model Features

Multi-dialect Support

Supports both Bokmål and Nynorsk variants of Norwegian simultaneously

Standardized Preprocessing

Utilizes standardized text preprocessing and SentencePiece tokenization to enhance translation quality

Language Tag Support

Supports specifying target language variants by adding language tags (>>id<<)

Model Capabilities

German-to-Norwegian text translation

Supports Bokmål output

Supports Nynorsk output

Use Cases

Text Translation

Daily Conversation Translation

Translate German daily conversations into Norwegian

BLEU score 33.2

Simple Document Translation

Translate simple German documents into Norwegian

🚀 deu-nor Translation Model

This is a translation model for converting German to Norwegian. It provides specific model information, pre - processing steps, and benchmark scores.

🚀 Quick Start

The deu-nor model is designed for German to Norwegian translation. You can download the original weights and test set translations from the provided links below.

✨ Features

Language Pair: Translates from German (deu) to Norwegian (nno, nob).
Model Type: transformer-align
Pre - processing: Normalization + SentencePiece (spm4k,spm4k)
Language Token Requirement: A sentence initial language token in the form of >>id<< (id = valid target language ID) is required.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

No code examples are provided in the original document.

📚 Documentation

Model Information

Source Group: German
Target Group: Norwegian
OPUS Readme: deu - nor
Model: transformer - align
Source Language(s): deu
Target Language(s): nno, nob
Pre - processing: normalization + SentencePiece (spm4k,spm4k)
Language Token Requirement: A sentence initial language token in the form of >>id<< (id = valid target language ID) is required.
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.deu.nor	33.2	0.554

System Info

Property	Details
hf_name	deu - nor
source_languages	deu
target_languages	nor
opus_readme_url	https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/deu-nor/README.md
original_repo	Tatoeba - Challenge
tags	['translation']
languages	['de', 'no']
src_constituents	{'deu'}
tgt_constituents	{'nob', 'nno'}
src_multilingual	False
tgt_multilingual	False
prepro	normalization + SentencePiece (spm4k,spm4k)
url_model	https://object.pouta.csc.fi/Tatoeba-MT-models/deu-nor/opus-2020-06-17.zip
url_test_set	https://object.pouta.csc.fi/Tatoeba-MT-models/deu-nor/opus-2020-06-17.test.txt
src_alpha3	deu
tgt_alpha3	nor
short_pair	de - no
chrF2_score	0.5539999999999999
bleu	33.2
brevity_penalty	0.956
ref_len	32928.0
src_name	German
tgt_name	Norwegian
train_date	2020 - 06 - 17
src_alpha2	de
tgt_alpha2	no
prefer_old	False
long_pair	deu - 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