Cook4986

Matt Cook's repositories

Text corpora in virtual reality

Language:PythonMIT16 10

Yiddish pulp fiction (Shund) transcription/translation

Language:Jupyter Notebook2 10

Black Teacher Archive project code

Language:Jupyter Notebook1 10

Handwriting transcription (HTR) throughput, for processing the contents of documents in Harvard Library collections.

Language:Jupyter Notebook1 10

Digital Giza "Tomb" Generator

010

Super simple bag-of-words generator

Language:Jupyter Notebook010

Pre-processing, handwriting OCR, and transcription for Extra-Illustrated card catalog in Houghton Library

Language:PythonMIT010

Takes pdf input and outputs abbreviated pdf with keyword highlights. Returns Term-document matrix, Bi-gram and LDA topic analysis

Language:PythonGPL-3.0010

Create and fuzzy search bag-of-words generated from handwritten transcriptions

Language:Jupyter Notebook010

Searches Harvard Art Museum holdings by year and returns masked images, text file of classifications, and word cloud

Language:Python010

Resources for self hosted Hubs Cloud instances

Language:Shell000

Compare image IDs across IIIF manifest and .mets metadata files

Language:Jupyter NotebookMIT010

Scrape online staff directory for office locations and append CSV with that data

Language:Jupyter NotebookMIT010

Template workflow for OCR/HTR, querying, and NLP

Language:Jupyter Notebook020