Codesota · Computer Vision · Optical Character Recognition · lam(line-level)Tasks/Computer Vision/Optical Character Recognition
Optical Character Recognition · benchmark dataset · 2020 · EN

lam(line-level).

Dataset from Papers With Code

Submit a result ↵
§ 01 · Leaderboard

Best published scores.

14 results indexed across 2 metrics. Shaded row marks current SOTA; ties broken by submission date.

Primary
accuracy · higher is better
All metrics
test-cer, test-wer
test-cer
7 rows
#ModelOrgSubmittedPaper / codetest-cer
01HTR-ConvTextDAIR-GroupDec 2024HTR-ConvText: Leveraging Convolution and Textual Informa…2.70
02HTR-VT—Sep 2024HTR-VT: Handwritten Text Recognition with Vision Transfo… · code2.80
03OrigamiNet-24—Jun 2020OrigamiNet: Weakly-Supervised, Segmentation-Free, One-St… · code3.00
04OrigamiNet-18—Jun 2020OrigamiNet: Weakly-Supervised, Segmentation-Free, One-St… · code3.10
05OrigamiNet-12—Jun 2020OrigamiNet: Weakly-Supervised, Segmentation-Free, One-St… · code3.10
06TrOCR—Sep 2021TrOCR: Transformer-based Optical Character Recognition w… · code3.60
07GFCN—Dec 2020Recurrence-free unconstrained handwritten text recogniti… · code5.20
test-wer
7 rows
#ModelOrgSubmittedPaper / codetest-wer
01HTR-ConvTextDAIR-GroupDec 2024HTR-ConvText: Leveraging Convolution and Textual Informa…7.00
02HTR-VT—Sep 2024HTR-VT: Handwritten Text Recognition with Vision Transfo… · code7.40
03OrigamiNet-24—Jun 2020OrigamiNet: Weakly-Supervised, Segmentation-Free, One-St… · code11
04OrigamiNet-18—Jun 2020OrigamiNet: Weakly-Supervised, Segmentation-Free, One-St… · code11.10
05OrigamiNet-12—Jun 2020OrigamiNet: Weakly-Supervised, Segmentation-Free, One-St… · code11.20
06TrOCR—Sep 2021TrOCR: Transformer-based Optical Character Recognition w… · code11.60
07GFCN—Dec 2020Recurrence-free unconstrained handwritten text recogniti… · code18.50
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 04 · Literature

5 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies