This software can convert text in image into editable .docx file. Any PNG or JPEG image with text in it can be used to generate a .docx file.
This software pre-trained AI models for recognition of English charachters. This is done with the help of the Tesseract python package.
-
The Software has been divided into Frontend and Backend and can be used seperately in two different servers.
-
In Backend the required Python packages can be installed using the
requirements.txtfile -
sudo pip install -r requirements.txt -
In linux enviornment you may need to install additional package
sudo apt install tesseract-ocr -y -
Set the
.envmentioning the address of the frontend (.env.example provided) -
Run the
aapi.pyscript located inBackend/API -
send a
GETrequest to/usersendpoint. It should returnworks. That means it's working. -
Frontend Setup: Change the
Frontend/assets/js/custom.jsBackend URL to the url of the backend server. -
Deploy the frontend.
videoplayback.mp4
You are free to create an issue for the same and raise respective Pull Requests. We appriciate your effort!!
