wjbmattingly

fundus

A very simple news crawler with a funny name

ngram

The n-gram Language Model

dspy

DSPy: The framework for programming—not prompting—foundation models

st-link-analysis

A custom Streamlit component for link analysis, built with Cytoscape.js and Streamlit.

awesome-ai4lam

A list of awesome AI in libraries, archives, and museum collections from around the world 🕶️

LADaS

Layout Analysis Dataset with Segmonto (LADaS)

rich

Rich is a Python library for rich text and beautiful formatting in the terminal.

GLiREL

Generalist and Lightweight Model for Relation Extraction (Extract any relationship types from text)

latin_NER_model

Latin named entities recognition model

GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

shakespeare-and-company-social-readership

Code to accompany "The Afterlives of Shakespeare and Company in Online Social Readership"

Bend

A massively parallel, high-level programming language

negspacy

spaCy pipeline object for negating concepts in text

octra

OCTRA is a web-application for the orthographic transcription of audio files.

evoc

Embedding Vector Oriented Clustering

Novel_Pollen_Phylogenetic_Placement

Code for a variety of pollen recognition tasks, including classification, novelty detection, and phylogenetic placement

spacyex

SpaCyEx allows the creation of spaCy Matcher patterns with RegEx like syntax.

the-mvm.github.io

The Minimum Viable Model website and Jekyll theme.

html-css-js-portfolio-tutorial-2

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

typer

Typer, build great CLIs. Easy to code. Based on Python type hints.

gliner-spacy

A spaCy wrapper for GliNER

awesome-whisper

🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI

GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

text-clustering

Easily embed, cluster and semantically label text datasets

whisper-streamlit

this master thesis project is based on OpenAI Whisper with the goal to transcibe interviews

mlx

MLX: An array framework for Apple silicon

mlx-examples

Examples in the MLX framework

datamapplot

Creating beautiful plots of data maps

florida

simple tools to make my life easier