Opus-MT ET-RU Open Source Machine Translation Model - Achieve Efficient Translation from Estonian to Russian for Free

Opus Mt Et Ru

Developed by Helsinki-NLP

This is an Estonian to Russian machine translation model based on the transformer-align architecture, developed by the Helsinki-NLP team and released as part of the Tatoeba-Challenge project.

Machine Translation

Transformers

OtherOpen Source License:Apache-2.0 #Estonian-Russian translation #High-precision BLEU50 #SentencePiece preprocessing

Downloads 106

Release Time : 3/2/2022

Model Overview

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

Model Features

High-quality translation

Achieved high scores of 50.2 BLEU and 0.702 chr-F on the Tatoeba test set

Standardized preprocessing

Utilizes standardized + SentencePiece (spm32k) preprocessing technology

Open-source license

Released under Apache-2.0 license, allowing both commercial and research use

Model Capabilities

Estonian to Russian text translation

Handles standardized text

Supports SentencePiece tokenization

Use Cases

Language services

Document translation

Translate Estonian documents into Russian

High-quality translation results (BLEU 50.2)

Cross-language communication

Facilitates communication between Estonian and Russian speakers

🚀 est - rus Translation Model

This is a translation model focusing on translating Estonian to Russian, offering high - quality translation services with specific pre - processing and evaluation scores.

✨ Features

Language Pair: It supports translation from Estonian to Russian.
Model Type: The model used is transformer - align.
Pre - processing: It employs normalization and SentencePiece (spm32k, spm32k) for pre - processing.

📦 Installation

The README does not provide specific installation steps, so this section is skipped.

📚 Documentation

General Information

Source Group: Estonian
Target Group: Russian
OPUS Readme: est - rus

Model Details

Property	Details
Model Type	transformer - align
Source Language(s)	est
Target Language(s)	rus
Pre - processing	normalization + SentencePiece (spm32k, spm32k)
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.est.rus	50.2	0.702

System Info

hf_name: est - rus
source_languages: est
target_languages: rus
opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/est-rus/README.md
original_repo: Tatoeba - Challenge
tags: ['translation']
languages: ['et', 'ru']
src_constituents: {'est'}
tgt_constituents: {'rus'}
src_multilingual: False
tgt_multilingual: False
prepro: normalization + SentencePiece (spm32k, spm32k)
url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/est-rus/opus-2020-06-17.zip
url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/est-rus/opus-2020-06-17.test.txt
src_alpha3: est
tgt_alpha3: rus
short_pair: et - ru
chrF2_score: 0.7020000000000001
bleu: 50.2
brevity_penalty: 0.988
ref_len: 3569.0
src_name: Estonian
tgt_name: Russian
train_date: 2020 - 06 - 17
src_alpha2: et
tgt_alpha2: ru
prefer_old: False
long_pair: est - rus
helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
port_machine: brutasse
port_time: 2020 - 08 - 21 - 14:41

📄 License

The model 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