HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Handwritten Text Recognition On Lam Line

평가 지표

Test CER
Test WER

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Test CER
Test WER
Paper TitleRepository
TrOCR3.611.6TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
GFCN5.218.5Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network
OrigamiNet-183.111.1OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
OrigamiNet-243.011.0OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
OrigamiNet-123.111.2OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
HTR-VT2.87.4HTR-VT: Handwritten Text Recognition with Vision Transformer
0 of 6 row(s) selected.