opus-mt-de-ms Open-Source Machine Translation Model - Achieve Accurate German to Malay Translation for Free

Opus Mt De Ms

Developed by Helsinki-NLP

This is a German-to-Malay (macrolanguage) machine translation model based on the transformer-align architecture, released by the Helsinki-NLP team.

Machine Translation

Transformers

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

Downloads 20

Release Time : 3/2/2022

Model Overview

This model focuses on German-to-Malay (macrolanguage) translation tasks, supporting multiple Malay variants including Indonesian and Standard Malay.

Model Features

Multilingual support

Supports translation for multiple Malay variants including Indonesian and Standard Malay.

Standardized preprocessing

Uses standardization and SentencePiece for text preprocessing to improve translation quality.

Language identifiers

Supports specifying target language variants by adding language identifiers.

Model Capabilities

German-to-Malay text translation

German-to-Indonesian text translation

Supports multiple Malay variants

Use Cases

Language translation

German-Malay document translation

Translate German documents into Malay or Indonesian.

BLEU score 34.0, chr-F score 0.607

Multilingual content localization

Provide localized content for users in Malay-speaking regions.

🚀 deu-msa Translation Model

This project focuses on German to Malay (macrolanguage) translation, providing a reliable model and related evaluation data.

🚀 Quick Start

This model is designed for German to Malay (macrolanguage) translation. You can download the original weights and test set translations from the following links:

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

✨ Features

Model Type: transformer-align
Source Languages: deu
Target Languages: ind zsm_Latn
Pre - processing: normalization + SentencePiece (spm32k,spm32k)
Language Token Requirement: A sentence initial language token is required in the form of >>id<< (id = valid target language ID)

📚 Documentation

Model Information

Property	Details
Model Type	transformer-align
Source Languages	deu
Target Languages	ind zsm_Latn
Pre - processing	normalization + SentencePiece (spm32k,spm32k)
Download Link (Original Weights)	opus-2020-06-17.zip
Test Set Translations Link	opus-2020-06-17.test.txt
Test Set Scores Link	opus-2020-06-17.eval.txt

System Info

hf_name: deu-msa
source_languages: deu
target_languages: msa
opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/deu-msa/README.md
original_repo: Tatoeba-Challenge
tags: ['translation']
languages: ['de', 'ms']
src_constituents: {'deu'}
tgt_constituents: {'zsm_Latn', 'ind', 'max_Latn', 'zlm_Latn', 'min'}
src_multilingual: False
tgt_multilingual: False
prepro: normalization + SentencePiece (spm32k,spm32k)
url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/deu-msa/opus-2020-06-17.zip
url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/deu-msa/opus-2020-06-17.test.txt
src_alpha3: deu
tgt_alpha3: msa
short_pair: de-ms
chrF2_score: 0.607
bleu: 34.0
brevity_penalty: 0.9540000000000001
ref_len: 3729.0
src_name: German
tgt_name: Malay (macrolanguage)
train_date: 2020-06-17
src_alpha2: de
tgt_alpha2: ms
prefer_old: False
long_pair: deu-msa
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.

🔍 Benchmarks

testset	BLEU	chr-F
Tatoeba-test.deu.msa	34.0	0.607

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