Skip to content
@Helsinki-NLP

Language Technology at the University of Helsinki

Projects and resources developed in the Language Technology Research Group at the University of Helsinki.

Popular repositories Loading

  1. Tatoeba-Challenge Tatoeba-Challenge Public

    Makefile 807 91

  2. Opus-MT Opus-MT Public

    Open neural machine translation models and web services

    Python 625 71

  3. OPUS-MT-train OPUS-MT-train Public

    Training open neural machine translation models

    Makefile 337 41

  4. prosody prosody Public

    Helsinki Prosody Corpus and A System for Predicting Prosodic Prominence from Text

    Python 235 39

  5. OpusFilter OpusFilter Public

    OpusFilter - Parallel corpus processing toolkit

    Python 102 18

  6. HBMP HBMP Public

    Sentence Embeddings in NLI with Iterative Refinement Encoders

    Python 79 16

Repositories

Showing 10 of 106 repositories
  • LLM-course-2024 Public

    Repository for the course Large Language Models and Generative AI for NLP

    Helsinki-NLP/LLM-course-2024’s past year of commit activity
    Jupyter Notebook 10 13 0 1 Updated Nov 26, 2024
  • Helsinki-NLP/swag_transformers’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Nov 26, 2024
  • mammoth Public

    MAMMOTH: MAssively Multilingual Modular Open Translation @ Helsinki

    Helsinki-NLP/mammoth’s past year of commit activity
    Python 22 MIT 3 12 (3 issues need help) 1 Updated Nov 25, 2024
  • Helsinki-NLP/OpusIndex’s past year of commit activity
    Python 0 0 0 0 Updated Nov 15, 2024
  • OpusDistillery Public Forked from mozilla/translations

    Training pipelines for Firefox Translations neural machine translation models (adapted for OPUS-MT and integrating GreenNLP metrics)

    Helsinki-NLP/OpusDistillery’s past year of commit activity
    Python 2 MPL-2.0 36 8 0 Updated Nov 15, 2024
  • swa_gaussian Public Forked from wjmaddox/swa_gaussian

    Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning" (Helsinki-NLP fork)

    Helsinki-NLP/swa_gaussian’s past year of commit activity
    Jupyter Notebook 0 BSD-2-Clause 82 0 0 Updated Nov 13, 2024
  • OPUS Public

    The Open Parallel Corpus

    Helsinki-NLP/OPUS’s past year of commit activity
    JavaScript 58 7 10 0 Updated Nov 10, 2024
  • lm-vs-mt Public

    A Comparison of Language Modeling and Translation as Multilingual Pretraining Objectives

    Helsinki-NLP/lm-vs-mt’s past year of commit activity
    Python 1 0 0 0 Updated Nov 9, 2024
  • shroom Public
    Helsinki-NLP/shroom’s past year of commit activity
    SCSS 4 0 0 0 Updated Nov 8, 2024
  • OPUS-CAT Public

    OPUS-CAT is a collection of software which make it possible to OPUS-MT neural machine translation models in professional translation. OPUS-CAT includes a local offline MT engine and a collection of CAT tool plugins.

    Helsinki-NLP/OPUS-CAT’s past year of commit activity
    C# 70 MIT 11 46 8 Updated Nov 1, 2024