Opus-mt-eu-de Open-source Machine Translation Model - Free and Efficient Translation from Basque to German

Opus Mt Eu De

Developed by Helsinki-NLP

This is a Basque to German 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 #Low-resource language translation #Transformer-based #SentencePiece preprocessing

Downloads 62

Release Time : 3/2/2022

Model Overview

This model is specifically designed for Basque to German text translation tasks, utilizing standardized preprocessing and SentencePiece tokenization techniques.

Model Features

Transformer-align Architecture

Utilizes the advanced transformer-align architecture to effectively handle Basque to German translation tasks.

Standardized Preprocessing

Employs standardized preprocessing and SentencePiece tokenization to enhance translation quality.

Multilingual Support

Focuses on bidirectional translation between Basque and German.

Model Capabilities

Text Translation

Basque to German Translation

Use Cases

Language Translation

Basque Text Translation

Translate Basque text into German

BLEU score 36.3, chr-F score 0.562

🚀 Eus - Deu Translation Model

This project focuses on the translation between Basque and German. It provides a specific model and related evaluation data to facilitate Basque - German translation tasks.

🚀 Quick Start

The project offers a ready - to - use translation model. You can download the original weights and test set translations through the following links:

Download original weights: opus-2020-06-16.zip
Test set translations: opus-2020-06-16.test.txt
Test set scores: opus-2020-06-16.eval.txt

✨ Features

Language Pair: Supports translation from Basque (eus) to German (deu).
Model Type: Uses the transformer-align model.
Pre - processing: Applies normalization and SentencePiece (spm12k,spm12k) for pre - processing.

📚 Documentation

Model Information

Property	Details
Model Type	transformer-align
Source Language	eus (Basque)
Target Language	deu (German)
Pre - processing	normalization + SentencePiece (spm12k,spm12k)
Download Link for Original Weights	opus-2020-06-16.zip
Test Set Translations Link	opus-2020-06-16.test.txt
Test Set Scores Link	opus-2020-06-16.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.eus.deu	36.3	0.562

System Info

hf_name: eus-deu
source_languages: eus
target_languages: deu
opus_readme_url: OPUS Readme
original_repo: Tatoeba-Challenge
tags: ['translation']
languages: ['eu', 'de']
src_constituents: {'eus'}
tgt_constituents: {'deu'}
src_multilingual: False
tgt_multilingual: False
prepro: normalization + SentencePiece (spm12k,spm12k)
url_model: Model Download
url_test_set: Test Set
src_alpha3: eus
tgt_alpha3: deu
short_pair: eu-de
chrF2_score: 0.562
bleu: 36.3
brevity_penalty: 0.953
ref_len: 3315.0
src_name: Basque
tgt_name: German
train_date: 2020-06-16
src_alpha2: eu
tgt_alpha2: de
prefer_old: False
long_pair: eus-deu
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