wietsedv

bertje

BERTje is a Dutch pre-trained BERT model developed at the University of Groningen. (EMNLP Findings 2020) "What’s so special about BERT’s layers? A closer look at the NLP pipeline in monolingual and multilingual models"

gpt2-recycle

As good as new. How to successfully recycle English GPT-2 to make models for other languages (ACL Findings 2021)

xpos

Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages (ACL 2022)

docker-calibre-server

Automatically updating slim Debian image with the latest Calibre Server

dumb

A Benchmark for Smart Evaluation of Dutch Models (EMNLP 2023)

low-resource-adapt

Code for the paper "Adapting Monolingual Models: Data can be Scarce when Language Similarity is High" (ACL Findings 2021)

dtw-numba

A faster Python DTW library with no precompiled code

acl-anthology

Data and software for building the ACL Anthology.

CEPEND

Contingent Event Pair Extractor for Natural Disasters

common-voice

Common Voice is part of Mozilla's initiative to help teach machines how real people speak.

conda-forge-pinning-feedstock

A conda-smithy repository for conda-forge-pinning.

dumbench

espnet

End-to-End Speech Processing Toolkit

espnet-feedstock

A conda-smithy repository for espnet.

nixpkgs

Nix Packages collection & NixOS

NLP-NL

pan19-cross-domain-authorship-attribution

ParallelWaveGAN

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN) with Pytorch

mojo

The Mojo Programming Language

staged-recipes

A place to submit conda recipes before they become fully fledged conda-forge feedstocks

WP24