![]() INFO:multilingual_document:Parsing document from pdf to image It takes a lot of time and basically is stuck after printing this : Pdf2text = PDF2Text(document=pdf_document) # create document for extraction with configurations !pip install multilingual-pdf2text=1.1.0įrom multilingual_pdf2text.pdf2text import PDF2Textįrom multilingual_model.document import Document Here is the code that i tried in colab: !pip install gTTS Thank you for making this awesome library.i am trying to make a bengali tafsir reader using your repository. Tesseract supports the following languages: Pdf2text = PDF2Text( document = pdf_document) ![]() # create document for extraction with configurations pdf_document = Document(ĭocument_path = '/Users/shahrukh/Desktop/multilingual-pdf2text/example/example.pdf', document import Document import logging logging. pdf2text import PDF2Text from multilingual_pdf2text.
0 Comments
Leave a Reply. |