Benjamin Minixhofer

nlprule. A fast, low-resource Natural Language Processing and Text Correction library written in Rust.

zett. Code for Zero-Shot Tokenizer Transfer

permon. A tool to monitor everything you want. Clean, simple, extensible and in one place.

tractjs. Run ONNX and TensorFlow inference in the browser.

tokenkit. A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.

gerpt2. German small and large versions of GPT2.

srx. A mostly compliant Rust implementation of the Segmentation Rules eXchange (SRX) 2.0 standard for text segmentation.

compoundpiece. Python

ukrainian-wechsel-models. Ukrainian NLP

bminixhofer.

decb. Promisified version of any npm module

CharSplit. Compound splitter for German

freecodecamp. My FreeCodeCamp projects.

ilps-nl-splitter. Perl

client. 🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.