collectivat/ladino-MT-models

Ladino Neural Machine Translation Models

OpenNMT-based models for Ladino (Judeo-Spanish) machine translation.

Models

• lad-eng/: Ladino ↔ English
• lad-spa/: Ladino ↔ Spanish
• lad-tur/: Ladino ↔ Turkish

Usage

These instructions were automatically generated by an LLM and are not tested.

import sentencepiece as spm
import torch
import onmt

# Load model
model_path = "lad-eng/model_lad-eng_step_100000.pt"
model = torch.load(model_path)

# Load sentencepiece
sp = spm.SentencePieceProcessor()
sp.load("lad-eng/sp.model")

Background

Ladino (also called Judeo-Spanish or Judezmo, ISO 639-3: lad) is the historical language of Sephardic Jews, descended from Old Castilian Spanish of the 15th century. After the Spanish Inquisition (1492), Sephardic Jews were expelled and welcomed into the Ottoman Empire, where they retained and evolved the language for over 530 years.

Today, Ladino is classified as a severely endangered language by UNESCO. This TTS model is part of efforts to preserve and revitalize the language through modern technology.

Citation

See: Preparing an Endangered Language for the Digital Age: The Case of Judeo-Spanish

Curation

This dataset was curated as part of the project "Judeo-Spanish: Connecting the Two Ends of the Mediterranean" carried out by Col·lectivaT and Sephardic Center of Istanbul within the framework of the "Grant Scheme for Common Cultural Heritage: Preservation and Dialogue between Turkey and the EU–II (CCH-II)" implemented by the Ministry of Culture and Tourism of the Republic of Turkey with the financial support of the European Union.

Contact

• Sephardic Center of Istanbul: [email protected]

Acknowledgments

The content of this dataset is the sole responsibility of Col·lectivaT and does not necessarily reflect the views of the European Union.

License

This dataset is released under the Creative Commons Attribution-NonCommercial 4.0 International License (CC-BY-NC-4.0). This means you are free to share and adapt the material for non-commercial purposes only, with appropriate attribution.

This repository is developed as part of project "Judeo-Spanish: Connecting the two ends of the Mediterranean" carried out by Col·lectivaT and Sephardic Center of Istanbul within the framework of the “Grant Scheme for Common Cultural Heritage: Preservation and Dialogue between Turkey and the EU–II (CCH-II)” implemented by the Ministry of Culture and Tourism of the Republic of Turkey with the financial support of the European Union. The content of this website is the sole responsibility of Col·lectivaT and does not necessarily reflect the views of the European Union.