Handwritten Text Recognition On Lam Line
Metrics
Test CER
Test WER
Results
Performance results of various models on this benchmark
Model Name | Test CER | Test WER | Paper Title | Repository |
|---|---|---|---|---|
| TrOCR | 3.6 | 11.6 | TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models | - |
| GFCN | 5.2 | 18.5 | Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network | - |
| OrigamiNet-18 | 3.1 | 11.1 | OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold | - |
| OrigamiNet-24 | 3.0 | 11.0 | OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold | - |
| OrigamiNet-12 | 3.1 | 11.2 | OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold | - |
| HTR-VT | 2.8 | 7.4 | HTR-VT: Handwritten Text Recognition with Vision Transformer | - |
0 of 6 row(s) selected.