lennartkeller Goto Github PK

auto_entity_indexing

block-recurrent-transformer-pytorch

Implementation of Block Recurrent Transformer - Pytorch

charsiug2p

Multilingual G2P in 100 languages

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

datasets-cmu_wilderness

CMU Wilderness Multilingual Speech Dataset

deeptextclustering

Deep text clustering with language models

ebooklib

Python E-book library for handling books in EPUB2/EPUB3 format -

exmlc

Library for extreme multiclass classification in Python

fast_al

fausteditiontutorial

germancoref

Adapted Dutch coreference resolution & dialogue analysis using deterministic rules for German

images

imsdb_epub

Scrape movie scripts from imsdb.com and convert them to Ebooks

informationretrieval2020

Repo for the exercises of the 2020 information retrieval lecture

jc_data

latex-mimosis

A minimal & modern LaTeX template for your (bachelor's | master's | doctoral) thesis

lennartkeller.github.io

lnn

_L_ennart's _N_eural _N_etwork modeling boilerplate code...

memorizing-transformers-pytorch

Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch

nlpaug

Data augmentation for NLP

pd-makefiles

My Makefiles to make slides, mostly using pandoc

phonepiece

phone inventory library

poutyne-transformers

Train 🤗-transformers models with Poutyne.

python_intro

Introduction into Python (in German!)

pythontrie

Simple implemation of a 'trie-tree' for text processing purposes (e.g stopword filtering)

roberta2longformer

Convert pretrained RoBerta models to various long-document transformer models

rom_real

rouge-score

Fork of google rouge score implementation

s2e-coref

salmonn

SALMONN: Speech Audio Language Music Open Neural Network