Opus Mt Dra En

🚀 dra-eng Translation Model

This project focuses on the translation between Dravidian languages and English. It provides a transformer-based model with specific pre - processing methods and offers various evaluation scores on different test sets.

🚀 Quick Start

The main function of this project is to translate from Dravidian languages (including Tamil, Kannada, Malayalam, Telugu) to English. You can download the original weights and test set translations from the provided links for further exploration.

✨ Features

• Language Support: Supports multiple Dravidian languages (ta, kn, ml, te, dra) to English translation.
• Model Type: Utilizes a transformer model for translation tasks.
• Pre - processing: Applies normalization and SentencePiece (spm32k, spm32k) for pre - processing.

📦 Installation

There is no specific installation command provided in the original document, so this section is skipped.

💻 Usage Examples

There is no code example provided in the original document, so this section is skipped.

📚 Documentation

dra - eng Translation Details

• Source Group: Dravidian languages
• Target Group: English
• OPUS Readme: dra - eng

Model Information

Benchmarks

System Info

• hf_name: dra - eng
• source_languages: dra
• target_languages: eng
• opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/dra-eng/README.md
• original_repo: Tatoeba - Challenge
• tags: ['translation']
• languages: ['ta', 'kn', 'ml', 'te', 'dra', 'en']
• src_constituents: {'tam', 'kan', 'mal', 'tel'}
• tgt_constituents: {'eng'}
• src_multilingual: True
• tgt_multilingual: False
• prepro: normalization + SentencePiece (spm32k, spm32k)
• url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/dra-eng/opus2m-2020-07-31.zip
• url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/dra-eng/opus2m-2020-07-31.test.txt
• src_alpha3: dra
• tgt_alpha3: eng
• short_pair: dra - en
• chrF2_score: 0.493
• bleu: 30.0
• brevity_penalty: 1.0
• ref_len: 10641.0
• src_name: Dravidian languages
• tgt_name: English
• train_date: 2020 - 07 - 31
• src_alpha2: dra
• tgt_alpha2: en
• prefer_old: False
• long_pair: dra - eng
• 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.