TraPrInq - Transcription model to recognize Portuguese handwritten texts from the 16th to 19th centuries

Description This model trained using the TraPrInq Project dataset, which encompasses a comprehensive collection of Portuguese handwritten documents from the 16th to 19th centuries. The dataset, made available through Open Science principles on Zenodo (Portuguese Handwriting 16th-19th c. Dataset), includes over 6,400 transcribed pages from the Portuguese Inquisition records, divided into nine training sets and one final validation set. The dataset was meticulously transcribed and curated by members of the TraPrInq project, ensuring the highest level of accuracy and alignment with paleographic transcription standards. The model benefits from these high-quality transcriptions and aims to facilitate the recognition of Portuguese historical manuscripts, addressing challenges like degraded texts, varying handwriting styles, and historical abbreviations. Model Details The model was trained by Weslley Oliveira with Kraken v.5.3.1 using: Datasets: Training set 146740 lines, validation set 16305 lines, Normalization: Unicode Normalization Form Decomposed (NFD). Specification: [1,120,0,1 Cr3,13,32 Do0.1,2 Mp2,2 Cr3,13,64 Do0.1,2 Mp2,2 Cr3,9,128 Do0.1,2 Mp2,2 Cr3,9,256 Do0.1,2 S1(1x0)1,3 Lbx600 Do0.1,2 Lbx600 Do.1,2 Lbx600 Do] Optimization: Ground truth corrections based on manual transcription of historical texts. The resulting model is designed to recognize Portuguese handwritten documents from a variety of historical contexts, with potential applications in digitization projects, archival research, and cultural heritage preservation. Results Report generated using random 10% of the dataset: 94.87% Character Accuracy 95.23% Character Accuracy (Case-insensitive) 95.90% Latin/Common Character Report 648265 Characters33233 Errors94.87% Character Accuracy95.23% Character Accuracy (Case-insensitive)80.18% Word Accuracy 13753 Insertions4271 Deletions15209 Substitutions Count Missed %Right512088 20991 95.90% Latin121963 5118 95.80% Common14214 2853 79.93% Inherited Reference Portuguese Handwriting 16th-19th c. - TraPrInq - https://zenodo.org/records/13986218e-Inquisition - Transcribing the court records of the Portuguese Inquisition (1536-1821) - https://traprinq.hypotheses.org/ kraken - Kraken is a turn-key OCR system optimized for historical and non-Latin script material - https://github.com/mittagessen/kraken

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2024-12-22
DOI
https://doi.org/10.5281/zenodo.14543904
Primary Topic
Animal Vocal Communication and Behavior
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

TraPrInq - Transcription model to recognize Portuguese handwritten texts from the 16th to 19th centuries

Zenodo (CERN European Organization for Nuclear Research)
Animal Vocal Communication and Behavior
article

TraPrInq - Transcription model to recognize Portuguese handwritten texts from the 16th to 19th centuries

article en

Abstract

Description This model trained using the TraPrInq Project dataset, which encompasses a comprehensive collection of Portuguese handwritten documents from the 16th to 19th centuries. The dataset, made available through Open Science principles on Zenodo (Portuguese Handwriting 16th-19th c. Dataset), includes over 6,400 transcribed pages from the Portuguese Inquisition records, divided into nine training sets and one final validation set. The dataset was meticulously transcribed and curated by members of the TraPrInq project, ensuring the highest level of accuracy and alignment with paleographic transcription standards. The model benefits from these high-quality transcriptions and aims to facilitate the recognition of Portuguese historical manuscripts, addressing challenges like degraded texts, varying handwriting styles, and historical abbreviations. Model Details The model was trained by Weslley Oliveira with Kraken v.5.3.1 using: Datasets: Training set 146740 lines, validation set 16305 lines, Normalization: Unicode Normalization Form Decomposed (NFD). Specification: [1,120,0,1 Cr3,13,32 Do0.1,2 Mp2,2 Cr3,13,64 Do0.1,2 Mp2,2 Cr3,9,128 Do0.1,2 Mp2,2 Cr3,9,256 Do0.1,2 S1(1x0)1,3 Lbx600 Do0.1,2 Lbx600 Do.1,2 Lbx600 Do] Optimization: Ground truth corrections based on manual transcription of historical texts. The resulting model is designed to recognize Portuguese handwritten documents from a variety of historical contexts, with potential applications in digitization projects, archival research, and cultural heritage preservation. Results Report generated using random 10% of the dataset: 94.87% Character Accuracy 95.23% Character Accuracy (Case-insensitive) 95.90% Latin/Common Character Report 648265 Characters33233 Errors94.87% Character Accuracy95.23% Character Accuracy (Case-insensitive)80.18% Word Accuracy 13753 Insertions4271 Deletions15209 Substitutions Count Missed %Right512088 20991 95.90% Latin121963 5118 95.80% Common14214 2853 79.93% Inherited Reference Portuguese Handwriting 16th-19th c. - TraPrInq - https://zenodo.org/records/13986218e-Inquisition - Transcribing the court records of the Portuguese Inquisition (1536-1821) - https://traprinq.hypotheses.org/ kraken - Kraken is a turn-key OCR system optimized for historical and non-Latin script material - https://github.com/mittagessen/kraken

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 62%
Animal Vocal Communication and Behavior
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.