William Mattingly's repositories
youtube-florence-table
Table detection with Florence.
tap-2024-vector-databases
This is my 2024 course for TAP Institute on Vector Databases and Semantic Searching.
bagpipes-spacy
Bagpipes spaCy is a collection of custom spaCy pipeline components designed to enhance text processing capabilities.
spacy-chunks
An easy way to chunk spaCy docs.
tap-2024-spacy-llms
This is the repository for my 2024 Tap Institute Course on spaCy with LLMs
ml-project-template
My template for machine learning projects
youtube-streamlit-link-analysis
A quick repository for using streamlit link analysis component.
gliner-finetune
A package for generating synthetic data and fine-tuning a gliner model.
catmus-analysis
A repo for analyzing the CATMuS dataset.
florence-2-finetune
Finetuning florence 2 on CATMuS.
medieval-htr
A demo for how to use TrOCR Medieval HTR models.
spacyex-demo
Demo for spaCyEx library.
catmus-train
The code for training TrOCR models from the CATMuS dataset.
GLiNER
Generalist model for NER (Extract any entity types from texts)
jekyll-theme-chirpy
A minimal, responsive, and feature-rich Jekyll theme for technical writing.
ReLERNN
Recombination Landscape Estimation using Recurrent Neural Networks
spacy-annoy
A package for doing semantic search with spaCy docs.
spacy-whisper
A spaCy pipeline designed to work with whisper outputs.
spcay-aligner
A component to identify and align person entities.
traveling-historian
The Minimum Viable Model website and Jekyll theme.