23.2 aztranslate quick start


Let’s quickly explore some examples to show off the various commands supported by the package.

A simple translate takes a sentence on the command line. The language is automatically detected and the resulting translation is to English by default (see the translate command for details):

$ ml translate aztranslate Selamat pagi
ms,1.0,en,good morning

The target language can be specified using -t or --to= with a country code. Suppose we want to translate to French (fr):

$ ml translate aztranslate --to=fr Selamat pagi

Many languages are supported, including Persian (i.e., Fairsi or fa):

$ ml translate aztranslate --to=fa Please direct me to the restaurant
en,1.0,fa,لطفا مرا به رستوران هدایت کنید

You can list the supported languages:

$ ml supported aztranslate
zh-Hans,ltr,Chinese Simplified,简体中文
zh-Hant,ltr,Chinese Traditional,繁體中文

The translation can be saved to file:

$ ml translate aztranslate --to fr Good morning | cut -d, -f4- > greeting_fr.txt
$ ml translate aztranslate --input greeting_fr.txt

Pipelines work great:

$ cat greeting_fr.txt | ml translate aztranslate

$ ml transcribe azspeech | ml translate aztranslate --to fr
en,1.0,fr,AI est assez bon à la traduction de nos jours.

But there are limits to the current state of the art in translation (see the limits command for details):

$ ml limits aztranslate
Limitations of Translations

Douglas Hofstadter, a professor of cognitive science and comparative

Your donation will support ongoing availability and give you access to the PDF version of this book. Desktop Survival Guides include Data Science, GNU/Linux, and MLHub. Books available on Amazon include Data Mining with Rattle and Essentials of Data Science. Popular open source software includes rattle, wajig, and mlhub. Hosted by Togaware, a pioneer of free and open source software since 1984. Copyright © 1995-2022 Graham.Williams@togaware.com Creative Commons Attribution-ShareAlike 4.0