Skip to main content

Tool for translating text from the screen and some more

Project description

Linter check Maintainability Static Badge

image

EN | RU

Advanced Screen Assistant. OCRHelper is able to translate text from the selected area. It is also possible to search for the meaning of a word using ChatGPT, as well as simply copy it to the clipboard.

Main features

  • High text recognition precision
  • OCR Helper for text recognition uses EasyOCR, which handles most of the daily text reading requirements.
  • Simple interface
  • The main idea was to make tool, that does not require manual adjustments for each case and convenient for everyday use.
  • Available translators: Google Translate, ChatGPT, ChatGPT with streaming display
  • Available recognition and translation languages: English, Russian, Japanese
  • Dictionary: mode for finding the meaning of a word using ChatGPT
  • Recognition: mode for only text recognition, can be used with the option to copy text to the clipboard

System requirements

  • Windows 10 build 19041 (20H1) / Windows 11
  • DirectX11
  • 1 GB free RAM
  • 5 GB free storage space/ 1 GB for without_cuda version
  • Nvidia GPU with CUDA SDK 11.8 support (GTX 750, 8xxM, 9xx series or later) (for mode using CUDA)

How to use

  1. Choose the version that suits you: the regular version weighs more and takes more time to start, but reads text faster, the without_cuda version is the opposite (you can download any of them here)
  2. Launch the application (The first launch will take much longer than the subsequent ones)
  3. Open the menu using CTRL + ALT + X or via the tray
  4. Open the settings
  5. Select the necessary languages for recognition (the fewer selected, the more accurate the recognition)
  6. Select a translator (you will need to enter an API-key to use GPT)
  7. (Optional) Change the color of the area selection in the palette
  8. Press CTRL + SHIFT + X to select an area and then translate
  9. Wait for the translation result

Usage Tips

Should install a non-standard font

This should be done to better display the application window

To do this, go to "ocrhelper/additional files", run "Rubik.ttf", click "install"

Use Borderless/Windowed modes in games (not Fullscreen)

It is necessary to display the translation window overlay correctly.

If the game doesn't have such mode, you can use external tools to make it borderless (e.g. Borderless Gaming)

Install the application on SSD

To reduce cold launch time with enabled EasyOCR engine (loading large EasyOCR model into RAM).

Error

If an error occurs while running the application, please create a new issue in the Issues tab. I will try to respond to the problem as soon as I see it.

TODO

  • Move app on PyQT
  • Add gamepad support for selecting area

For dev

  • Clone repository
  • git clone https://github.com/ReYaNOW/OCRHelper.git
    
  • Install dependencies
  • make install
    

    or

    make install_without_cuda
    

Dependencies

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ocrhelper-1.2.1.tar.gz (21.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ocrhelper-1.2.1-py3-none-any.whl (29.6 kB view details)

Uploaded Python 3

File details

Details for the file ocrhelper-1.2.1.tar.gz.

File metadata

  • Download URL: ocrhelper-1.2.1.tar.gz
  • Upload date:
  • Size: 21.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.1 CPython/3.11.4 Windows/10

File hashes

Hashes for ocrhelper-1.2.1.tar.gz
Algorithm Hash digest
SHA256 460f31f5a2700a4a89b6f706210311d9a324a112ff30ce907ecdf805a17323d5
MD5 f0ad25d1a26771ed10d331f2b62a4eb8
BLAKE2b-256 92089d72d7f39ec0f7631c3f2d24034b0aa3843e06f19712bf61bcf201b95ae4

See more details on using hashes here.

File details

Details for the file ocrhelper-1.2.1-py3-none-any.whl.

File metadata

  • Download URL: ocrhelper-1.2.1-py3-none-any.whl
  • Upload date:
  • Size: 29.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.1 CPython/3.11.4 Windows/10

File hashes

Hashes for ocrhelper-1.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 8b1199a77fb39e50ace767a3913f8ad0f275bc73c8ab872489dc3f04388a1905
MD5 6c9351baf37ec536de94ff7fdae084bb
BLAKE2b-256 2a895443bcb9166db36ec50291c31d267eed08151c93837d0bfefe86410df570

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page