Opus Mt Et En
A machine translation model from Estonian to English based on Transformer architecture, developed by the Helsinki-NLP team and trained using the OPUS dataset.
Downloads 4,944
Release Time : 3/2/2022
Model Overview
This is a neural machine translation model for translating Estonian to English, employing Transformer architecture and SentencePiece preprocessing techniques.
Model Features
Transformer-based architecture
Utilizes advanced Transformer model architecture to deliver high-quality translation results
SentencePiece preprocessing
Employs SentencePiece for text normalization and tokenization
Trained on OPUS dataset
Trained on the large-scale multilingual parallel corpus OPUS
Model Capabilities
Estonian to English text translation
Handling news text translation
Handling daily conversation translation
Use Cases
News translation
News content translation
Translating Estonian news into English
Achieved a BLEU score of 30.1 on the newsdev2018 test set
Daily communication
Dialogue translation
Translating daily conversation content
Achieved a BLEU score of 59.9 on the Tatoeba test set
Featured Recommended AI Models
ยฉ 2025AIbase