Opus-mt-gl-pt Open Source Machine Translation Model - Free Translation between Galician and Portuguese

Opus Mt Gl Pt

Developed by Helsinki-NLP

This is a Transformer-based machine translation model from Galician to Portuguese, developed by the Helsinki-NLP team.

OtherOpen Source License:Apache-2.0 #High-precision translation #Specialized for minority languages #SentencePiece tokenization

Downloads 37

Release Time : 3/2/2022

Model Overview

This model is specifically designed for text translation tasks from Galician (gl) to Portuguese (pt), employing standardized preprocessing and SentencePiece tokenization techniques.

Model Features

High-precision translation

Achieved high scores of 57.9 BLEU and 0.758 chr-F on the Tatoeba test set

Standardized preprocessing

Utilizes standardized preprocessing and SentencePiece tokenization (spm4k)

Lightweight model

Based on Transformer alignment architecture, suitable for resource-limited environments

Model Capabilities

Text translation

Cross-language conversion

Natural language processing

Use Cases

Language services

Document translation

Automatically translate Galician documents into Portuguese

Translation quality reaches 57.9 BLEU score

Cross-language communication

Assist real-time communication between Galician and Portuguese speakers

Education

Language learning aid

Help Galician speakers learning Portuguese through comparative study

🚀 glg-por

This translation model focuses on converting Galician to Portuguese.
Check the OPUS readme: glg-por

✨ Features

Language Support: Supports Galician (glg) as the source language and Portuguese (por) as the target language.
Model Type: Utilizes the transformer-align model.
Pre - processing: Applies normalization and SentencePiece (spm4k,spm4k) for pre - processing.

📦 Installation

No installation steps are provided in the original document.

📚 Documentation

Model Information

Property	Details
Source Group	Galician
Target Group	Portuguese
Model Type	transformer-align
Source Language(s)	glg
Target Language(s)	por
Pre - processing	normalization + SentencePiece (spm4k,spm4k)
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

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.glg.por	57.9	0.758

System Info

hf_name: glg-por
source_languages: glg
target_languages: por
opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/glg-por/README.md
original_repo: Tatoeba-Challenge
tags: ['translation']
languages: ['gl', 'pt']
src_constituents: {'glg'}
tgt_constituents: {'por'}
src_multilingual: False
tgt_multilingual: False
prepro: normalization + SentencePiece (spm4k,spm4k)
url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/glg-por/opus-2020-06-16.zip
url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/glg-por/opus-2020-06-16.test.txt
src_alpha3: glg
tgt_alpha3: por
short_pair: gl-pt
chrF2_score: 0.758
bleu: 57.9
brevity_penalty: 0.977
ref_len: 3078.0
src_name: Galician
tgt_name: Portuguese
train_date: 2020-06-16
src_alpha2: gl
tgt_alpha2: pt
prefer_old: False
long_pair: glg-por
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