English to Assamese, and Assamese 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 Assamese circular comes back as an English circular, and an English notice as a Assamese 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 Assamese is set in Noto Sans Bengali, as real Unicode text you can search and edit; if that font is not on your computer, choose any Assamese 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 Assamese
Assamese shares most of its letters with Bengali, and a translation that slipped into Bengali would look almost right. The test notice did not: it used ৰ, the Assamese ra, throughout (ধাৰা, নিৰ্মাণ), and the Assamese word for rupees, টকা. The machine check counted the script, and the English-to-Assamese text was all Assamese.
The weaker direction is into Assamese from another Indian language: from Odia, a sentence sometimes stays in Odia, highlighted. Translating from English, or from Assamese into English, is not affected.
What was measured for Assamese
Before Assamese was switched on, the production pipeline translated the test notice from English into Assamese 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 Assamese side was written in the Assamese 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 Assamese 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 Assamese writer would put it.
Assamese 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 Assamese OCR, correct what needs correcting, and translate the Word file that comes out. Assamese set in an old font such as Geetanjali 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. Assamese OCR reads scans of printed Assamese, and its Word file can be translated straight away.