OSDF project

CUBoulder_Garcia

PI: Diego Garcia · University of Colorado Boulder

Business

Fine tuning an OCR engine. Using the fine-tuned engine to get textual data from scanned documents. Also applying text mining models on the extracted text.

5.1 TB

Data delivered over the OSDF

11,664

Jobs

8.2K

Files via OSDF

1K

CPU hours

0

GPU hours

Cumulative usage · Jul 2, 2025 – Jul 2, 2026

Get involved

Bring your data onto the fabric.

Request an access point and connect your first repository in an afternoon — facilitation is free.