English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The laws of model size, data volume, computation and model performance havebeen extensively studied in the field of Natural Language Processing (NLP).However, the scaling laws in Optical Character Recognition (OCR) have not yetbeen investigated. To address this, we conducted comprehensive studies thatinvolved examining the correlation between performance and the scale of models,data volume and computation in the field of text recognition.Conclusively, thestudy demonstrates smooth power laws between performance and model size, aswell as training data volume, when other influencing factors are held constant.Additionally, we have constructed a large-scale dataset called REBU-Syn, whichcomprises 6 million real samples and 18 million synthetic samples. Based on ourscaling law and new dataset, we have successfully trained a scene textrecognition model, achieving a new state-ofthe-art on 6 common test benchmarkswith a top-1 average accuracy of 97.42%.

Large OCR Model:An Empirical Study of Scaling Law for OCR