Opus-mt-bg-ru Open-source Machine Translation Model - Achieve Efficient Bulgarian to Russian Translation for Free

Opus Mt Bg Ru

Developed by Helsinki-NLP

This is a Bulgarian to Russian machine translation model based on Transformer architecture, released by the Helsinki-NLP team.

Machine Translation

Transformers

OtherOpen Source License:Apache-2.0 #Slavic language translation #High-precision translation #Standardized preprocessing

Downloads 80

Release Time : 3/2/2022

Model Overview

This model is specifically designed for translating Bulgarian text into Russian, utilizing standardized preprocessing and SentencePiece tokenization techniques.

Model Features

Multi-format input support

Supports both native Bulgarian script and Latin script transliteration as input formats

Standardized preprocessing

Employs standardized preprocessing pipeline to enhance translation quality

SentencePiece tokenization

Uses a 32k vocabulary SentencePiece tokenizer for text processing

Model Capabilities

Bulgarian to Russian text translation

Processing Bulgarian text in Latin script transliteration

Use Cases

Language services

Document translation

Translating Bulgarian documents into Russian

Achieved 48.5 BLEU score on Tatoeba test set

Cross-language communication

Facilitating communication between Bulgarian and Russian speakers

🚀 bul-rus Translation Model

This project focuses on the translation from Bulgarian to Russian, providing a reliable translation solution with specific model and evaluation metrics.

🚀 Quick Start

The bul-rus model is designed for Bulgarian to Russian translation. You can download the original weights and test set translations from the provided links to start using the model.

✨ Features

Language Pair: Translates from Bulgarian (bul, bul_Latn) to Russian (rus).
Model Type: Utilizes the transformer model.
Pre - processing: Applies normalization and SentencePiece (spm32k,spm32k).

📦 Installation

The original weights of the model can be downloaded from opus-2020-07-03.zip.

💻 Usage Examples

There are no specific code examples provided in the original README. If you want to use the model, you can use the downloaded weights and relevant pre - processing methods for translation tasks.

📚 Documentation

Model Information

Property	Details
Source Group	Bulgarian
Target Group	Russian
OPUS Readme	bul-rus
Model Type	transformer
Source Language(s)	bul, bul_Latn
Target Language(s)	rus
Pre - processing	normalization + SentencePiece (spm32k,spm32k)
Download Original Weights	opus-2020-07-03.zip
Test Set Translations	opus-2020-07-03.test.txt
Test Set Scores	opus-2020-07-03.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.bul.rus	48.5	0.691

System Info

hf_name: bul-rus
source_languages: bul
target_languages: rus
opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/bul-rus/README.md
original_repo: Tatoeba-Challenge
tags: ['translation']
languages: ['bg', 'ru']
src_constituents: {'bul', 'bul_Latn'}
tgt_constituents: {'rus'}
src_multilingual: False
tgt_multilingual: False
prepro: normalization + SentencePiece (spm32k,spm32k)
url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/bul-rus/opus-2020-07-03.zip
url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/bul-rus/opus-2020-07-03.test.txt
src_alpha3: bul
tgt_alpha3: rus
short_pair: bg-ru
chrF2_score: 0.691
bleu: 48.5
brevity_penalty: 1.0
ref_len: 7870.0
src_name: Bulgarian
tgt_name: Russian
train_date: 2020-07-03
src_alpha2: bg
tgt_alpha2: ru
prefer_old: False
long_pair: bul-rus
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