Split folders with files (e.g. images) into training, validation and test (dataset) folders.
Functions to preprocess and normalize text.
Reconstruct the original continuous text from PDFs with language models
Dehyphenation of broken text (mainly German), i.e., extracted from a PDF
Flair's language models without unnecessary dependencies
Python Library to Construct Word Embeddings for Small Data
Preprocess German texts for serious NLP.
A Python package (using a Docker image under the hood) to lemmatize German texts.
Text Classification Library for Keras
Fetch a URL via the latest Wayback Machine Snapshot
Adding retries to Requests.get() with exponential backoff
Using MediaWiki's API, retrieve pages that belong to a given category
Visualize Your Deep Learning Training in Static Graphics