English to Sanskrit, and Sanskrit 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 fileтАЩs own and only the words change, so a Sanskrit circular comes back as an English circular, and an English notice as a Sanskrit 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 conversionтАЩs doing.
Translated Sanskrit is set in Noto Sans Devanagari, as real Unicode text you can search and edit; if that font is not on your computer, choose any Sanskrit 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 Sanskrit
As in Kannada, the year of the Act came back at the end of the first sentence, after the verb: рдЖрдордиреНрддреНрд░рд┐рддрд╛рдирд┐ рд╕рдиреНрддрд┐, 2016ред The year is kept, but it no longer stands beside the ActтАЩs name. Sanskrit word order is free, and a number tied to a name can move away from it.
The test was a modern administrative notice, and the machine translates Sanskrit as modern prose. It was not tested on verse, on a commentary, or on a text with sandhi across long compounds, and no metre is kept. Use it to get the sense of a document, not as a translation of scripture or a scholarly text.
What was measured for Sanskrit
Before Sanskrit was switched on, the production pipeline translated the test notice from English into Sanskrit 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 Sanskrit side was written in the Devanagari 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 Sanskrit 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 Sanskrit writer would put it.
Sanskrit 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 Sanskrit OCR, correct what needs correcting, and translate the Word file that comes out. Sanskrit set in an old Devanagari font such as Kruti Dev pastes as Latin letters; convert it to Unicode with the Kruti Dev converter first, then translate.
Footnotes, endnotes and comments are not translated yet, and the result says so. Text inside a picture is not translated. Sanskrit OCR reads scans of printed Sanskrit, and its Word file can be translated straight away.