Microsoft announced that the built-in document translation function of azure translator can now scan and translate PDF documents The company said that users no longer need to preprocess documents through OCR engine before trying to translate documents. Azure translator launched the document translation function a year ago, which can translate multiple documents into more than 110 languages and dialects at one time. Today's update means that PDF files are now supported in addition to word and PowerPoint files.
When explaining some functions, Microsoft said that the document translation function has now become more intelligent and can
● identify whether the PDF document contains scanned image content,
● route the PDF containing the scanned image content to the internal OCR engine to extract the text,
● reconstruct the translated content into regular text PDF while retaining the original layout and structure.
The scanning function is applicable to 110 languages and target languages, but it is only applicable to 87 languages. Microsoft has promised to increase support for more at "the right time".
Microsoft said it could start using the new features without changing the code, and all PDFs could be submitted to translator immediately. The new features won't cost customers more. Provide two pricing plans for document translation through azure; They include pay as you go plans and D3 quantity discount plans for higher quantities. aka.ms/TranslatorPricing