# Deseret Alphabet Manuscript Hackathon — Data

来源：https://www.kaggle.com/competitions/deseret-alphabet-manuscript-hackathon/data

采集时间：2026-10-19T09:32:39Z

In this competition you are tasked with transcribing lines of Deseret Alphabet images into unicode representations. The data is provided as images of various sizes that capture the content of a single line in a manuscript. You will develop a model that will transcribe each line in the **test/images/** directory and creating a submission csv file in the style of **sample_submission.csv**.

## Files

*   **train/images/** Contains transcribed png files of Deseret lines 
*   **train/labels/** Contains the corresponding labels to the ids of the train images. ex: **train/images/000cf4502.png** has transcription in **train/labels/000cf4502.txt**: 𐐮𐑌 𐐸𐐮𐑆 𐐿𐐮𐑍𐐼𐐲𐑋.
*   **test/images/** Contains unlabeled png files for your model to transcribe into Deseret to submit to the competition
*   **sample_submission.csv** - a sample submission file in the correct format

The images for this competition are courtesy of the Church History Library of the Church of Jesus Christ of Latter-day Saints, [CR 244 415](https://catalog.churchofjesuschrist.org/record/ab7480c3-3a13-4e80-8d2f-8d140caf78bd/0?view=browse&lang=eng).

The labels for this competition are courtesy of: Illinois Deseret Consortium. 2025. _Deseret (Unicode) transcription of the New Testament_. Accessed November 4, 2025, from http://faculty.las.illinois.edu/rshosted/deseret.html.