Skip to content

现成的OCR,支持80多种语言和所有流行的书写脚本,包括拉丁语、中文、阿拉伯语、梵文、西里尔文等。Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

active 2023-08-152026-08-12 (UTC)

Partial coverage20,529 / 26,285 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-14 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
7K
Pushes
10
Pull requests
47
Issues
142
Stars
5.9K
Forks
616

Activity over time

Daily event counts in the loaded window

Line chart, 1094 days from 2023-08-15 to 2026-08-12. Pushes: 10 total, peak 8 in a day. Pull requests: 47 total, peak 14 in a day. Issues: 142 total, peak 4 in a day. Comments: 359 total, peak 6 in a day. Stars: 5,851 total, peak 32 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#1425AakashKumarMissrani2026-03-06 19:09
    Collaboration Opportunity – OCR Model Development for Sindhi Language
  • Issue comment#815mattcaste2026-01-27 16:13
    Easyocr memory leak
  • Issue#1446yurivict2025-11-29 20:26
    The '-l LANG' argument should be optional or there should be '-l none'
  • Issue#1443LeonZion-Room2025-11-10 05:19
    Can't satisfied the eng-text
  • Issue comment#1438ishandutta20072025-11-08 16:52
    model size
  • Pull request#1440sharmy2025-10-19 11:51
  • Issue#1407p-vdp2025-10-15 01:56
    ValueError: too many values to unpack (expected 2) -- Reader.readtext() fails on JPEG input
  • Issue comment#1419micseydel2025-10-03 22:52
    Don't pin memory if device not set to use an accelerator.
  • Issue#1436oosakadayo2025-09-26 22:32
    Japanese just doesn't work, pretty much at all.
  • Pull request#1130pronoym992025-09-20 06:06
  • Issue comment#1378ppaauuoo2025-09-18 08:05
    RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
  • Issue comment#1423Basel-Mohamed2025-09-13 10:25
    Arabic OCR Training problem
  • Issue comment#364Daniel5952025-09-10 11:47
    Orientation detection
  • Pull request#1434David-Magdy2025-09-03 13:49
  • Issue comment#1378mengfoong-dev2025-08-23 16:44
    RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
  • Issue comment#1195Basel-Mohamed2025-08-23 14:06
    error in fine tune arabic model
  • Issue comment#1378VicentAvaria2025-08-21 08:53
    RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
  • Issue comment#686eadmaster2025-08-20 10:12
    OCR Vertical Japanese texts?
  • Issue#1374Mehdi-i2025-08-19 23:07
    EasyOCR academic paper
  • Issue comment#1430ViktorZam2025-08-16 12:47
    I can't train the model to recognize a single character
  • Issue comment#1419codingbotPark2025-08-09 14:36
    Don't pin memory if device not set to use an accelerator.
  • Issue comment#1083jtuttas2025-08-06 13:47
    Jupyter kernel dies every time I try to use easyocr following a youtube tutorial's Kaggle notebook
  • Issue#1429ocean-zhc2025-08-06 08:09
    数据错位
  • Pull request#14280x726f6f6b69652025-08-03 18:33
  • Pull request#1426Ai-Engineer0792025-07-29 12:15

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 5,851 stars here means stars gained during the window, not the repo's star count.