English to Gujarati, and Gujarati to English
Both directions work the same way. A Word file is edited where it stands: every paragraph style, table, list, header, footer and page setting stays the file’s own and only the words change, so a Gujarati circular comes back as an English circular, and an English notice as a Gujarati one, with its centred heading, numbered list and bordered table where they were. A PDF with selectable text is first turned into a Word file and then translated, so the result is a Word file you can edit, and how closely it follows the PDF is the PDF-to-Word conversion’s doing.
Translated Gujarati is set in Noto Sans Gujarati, as real Unicode text you can search and edit; if that font is not on your computer, choose any Gujarati font in Word. Numbers, dates, section references, amounts, times of day, e-mail addresses and web addresses are taken out before a sentence is sent and put back afterwards, and an answer in which one does not come back exactly once is not accepted. A sentence that still cannot be translated stays in the source language and is highlighted yellow; it is never dropped, and never filled in with a guess.
What to read carefully in the Gujarati
The Act’s name came back as હાઉસિંગ એક્ટ, the English words written in Gujarati letters, not as a Gujarati name for the Act. Both are seen in Gujarati writing, and which is right depends on the document: a government notice usually has an official Gujarati name, which the machine does not know. Check the names of acts, schemes and offices against the names your department uses.
Everything else in the sample was plain Gujarati, and it read back into English almost word for word.
What was measured for Gujarati
Before Gujarati was switched on, the production pipeline translated the test notice from English into Gujarati and back. In both directions 6 of 6 protected items came back exactly: the section reference, the year, the date, the amount, the e-mail address and the web address. The Gujarati side was written in the Gujarati script, and the English read back close to the original. A Word notice with a heading, a centred line with a bold date, a numbered list, a table, a tab, a header and a footer was also translated into Gujarati and back, and its paragraph settings, table grid, page setup, header and footer were identical to the source, on the same number of pages.
That is a check of the machinery, not of the language. It says the tool kept your numbers and your layout; it does not say every sentence reads the way a Gujarati writer would put it.
Gujarati in a scan or an old font
A scanned PDF has no text to translate, so it is refused rather than guessed at. Read it first with Gujarati OCR, correct what needs correcting, and translate the Word file that comes out. Gujarati set in an old font such as LMG Arun or Krishna pastes as Latin letters; convert it to Unicode with the legacy converter first, then translate.
Footnotes, endnotes and comments are not translated yet, and the result says so. Text inside a picture is not translated. Gujarati OCR reads scans of printed Gujarati, and its Word file can be translated straight away.