Giter VIP home page Giter VIP logo

argos-translate's Introduction

Argos Translate

Demo | Website | Docs | Forum | Video intro | GitHub

Open-source offline translation library written in Python

Argos Translate uses OpenNMT for translations, SentencePiece for tokenization, Stanza for sentence boundary detection, and PyQt for GUI. Argos Translate can be used as either a Python library, command-line, or GUI application. LibreTranslate is an API and web-app built on top of Argos Translate.

Argos Translate supports installing model files which are a zip archive with a ".argosmodel" extension with the data needed for translation.

Argos Translate also manages automatically pivoting through intermediate languages to translate between languages that don't have a direct translation between them installed. For example, if you have a es ➔ en and en ➔ fr translation installed you are able to translate from es ➔ fr as if you had that translation installed. This allows for translating between a wide variety of languages at the cost of some loss of translation quality.

Supported languages

Arabic, Azerbaijani, Chinese, Czech, Dutch, English, Esperanto, Finnish, French, German, Greek, Hindi, Hungarian, Indonesian, Irish, Italian, Japanese, Korean, Persian, Polish, Portuguese, Russian, Slovak, Spanish, Swedish, Turkish, Ukranian, Vietnamese

Screenshots

GUI

Screenshot Screenshot2 Argos Translate macOS Screenshot

Installation

Install from PyPI

Argos Translate is available from PyPI and can be easily installed or updated with pip.

pip3 install argostranslate

Install GUI:

pip3 install argostranslategui

Installation for macOS

  1. Download the latest macOS release.
  2. Extract the archive.
  3. Copy the .app file to the Applications directory.

Python source installation

Download a copy of this repo and install with pip.

git clone https://github.com/argosopentech/argos-translate.git
cd argos-translate
pip install -e .

Examples

from argostranslate import package, translate

# Install .argosmodel package
package.install_from_path('en_es.argosmodel')

installed_languages = translate.get_installed_languages()

# >>> [lang.code for lang in installed_languages]
# >>> ['en', 'es']

translation_en_es = installed_languages[0].get_translation(installed_languages[1])
translation_en_es.translate("Hello World!")

# >>> '¡Hola Mundo!'

Web App Screenshot

const res = await fetch("https://translate.argosopentech.com/translate", {
	method: "POST",
	body: JSON.stringify({
		q: "Hello!",
		source: "en",
		target: "es"
	}),
	headers: {
		"Content-Type": "application/json"}
	});

console.log(await res.json());

{
    "translatedText": "¡Hola!"
}

Graphical user interface

The GUI code is in a separate repository.

GPU Acceleration

To enable GPU support, you need to set the ARGOS_DEVICE_TYPE env variable to cuda or auto.

$ ARGOS_DEVICE_TYPE=cuda argos-translate --from-lang en --to-lang es "Hello World"
Hola Mundo

The above env variable instructs CTranslate2 to use cuda. if you encounter any issues with GPU inference please reference the CTranslate2 documentation.

Run Argos Translate!

GUI

Run the GUI version of Argos Translate.

argos-translate-gui

When installing with snap a .desktop file should also be installed which will make Argos Translate available from the desktop menu.

Languages are chosen as drop down choices. More languages pairs can be installed.

The left text box translates into the right box.

Example workflow translating from Vietnamese into English:

  1. Set the left drop down to Vietnamese and the right drop down to English.
  2. Replace the default text Text to translate from in the left text box with some text in Vietnamese. A quick way to do this is to click in the left text box and press the keyboard shortcut CTRL+a to select all and then CTRL+v to paste.
  3. Wait patiently.
  4. When text appears in the right text box, read the translation!

If the output looks similar to the input, try changing the origin language as some languages appear similar if you are unfamiliar with them.

Run the command line version of Argos Translate.

argos-translate

Translate a string from English to Spanish.

Note: If you do not have the language pair that you are calling installed, you will get a Traceback error.

argos-translate --from-lang en --to-lang es "Hello World."
Hola Mundo

Translate longer text piped into argos-translate.

echo "Text to translate" | argos-translate --from-lang en --to-lang es
Texto para traducir

HTML Translation

The translate-html library is built on top of Argos Translate and Beautiful Soup and parses and translates HTML. The LibreTranslate API also has support for translating HTML.

Files Translation

The argos-translate-files library is built on top of Argos Translate and parses and translates files. The LibreTranslate API also has support for translating files.

Uninstall

If you want to uninstall Argos Translate, you may choose the applicable method.

Uninstall PYPI/pip package

If you installed Argos Translate via pip you can uninstall it using

python3 -m pip uninstall argostranslate

You may choose to also delete temporary and cached files:

rm -r ~/.local/cache/argos-translate
rm -r ~/.local/share/argos-translate

Uninstall Snap

The following command will uninstall the snap package.

sudo snap remove argos-translate argos-translate-base-langs

If you installed additional language packs, you might want to remove them as well, e.g.

sudo snap remove argos-translate-de-en

Adding language pair models from the graphical interface

Language pairs are on average 100MB each.

Installing new pairs through the GUI

  1. Open Argos Translate: argos-translate-gui
  2. Click on the Manage Packages menu item.
  3. Click on the Download packages button.
  4. Click on the down arrow beside a language pair that you want to add.
  5. Wait for the hourglass icon to change into a check mark icon.
  6. Repeat the last two steps until you have all of the language pairs that you want.
  7. Click on the X in the top right to close the Download packages window.
  8. Click on the X in the top right to close the Manage Packages window.

Note: The Download packages screen does not seem to have a scroll bar so you will probably need to follow the next set of instructions to import new pairs through the GUI.

Importing new pairs through the GUI

  1. Download or make new pairs. Model links can be downloaded from this page or this JSON file.
  2. Open Argos Translate: argos-translate-gui
  3. Click on the Manage Packages menu item.
  4. Click on the Install package file button.
  5. Navigate to where you downloaded the new language pairs, click on the .argosmodel file, and click on the Open button.
  6. Repeat the last two steps until you have all of the language pairs that you want.
  7. Click on the X in the top right to close the Manage Packages window.

Importing new pairs through the CLI

  1. Update list of available language pairs: argospm update
  2. List all available language pairs: argospm search
  3. Install new pair syntax: argospm install *lang_pair_name*

For example, install Turkish to English pair: argospm install translate-tr_en

Optionally, you could install all language pairs using BASH.

for i in $(argospm search | sed 's/:.*$//g'); do argospm install $i ; done

Removing a pair through the GUI

  1. Open Argos Translate: argos-translate-gui
  2. Click on the Manage Packages menu item.
  3. Click on the trash can icon besides the pair you want to remove.
  4. Click on the X in the top right to close the Manage Packages window.

Removing a pair through the CLI

  1. Remove the Turkish to English pair: argospm remove translate-tr_en

Optionally, you could remove all language pairs using BASH if you need to free space fast.

for i in $(argospm list); do argospm remove $i ; done

Related Projects

Contributing

Awesome Humane Tech

Contributions are welcome! Available issues are on the GitHub issues page. Contributions of code, data, and pre-trained models can all be accepted.

Support

For support please use the LibreTranslate Forum or GitHub Issues.

For questions about CTranslate2 or general machine translation research the OpenNMT Forum is a good resource.

Services

Custom models trained on your own data are available for $1000/each (negotiable).

Managed hosting for $1000/mo.

Donate

If you find this software useful donations are appreciated.

  • GitHub Sponsor
  • PayPal
  • Bitcoin: 16UJrmSEGojFPaqjTGpuSMNhNRSsnspFJT
  • Ethereum: argosopentech.eth
  • Litecoin: MCwu7RRWeCRJdsv2bXGj2nnL1xYxDBvwW5
  • Bitcoin cash: qzqklgjpgutdqqlhcasmdd2hkqcelw426sxzk5qtne
  • Filecoin: f1nrnpmjxn27amidyiqrzq5mxihdo2trh2oijw2sq
  • Basic Attention Token: 0x8a16f26D277f924B04FCA5ECec64b76B5410A06c
  • Cheap Eth: 0x996133E61b81c300a37ACa9b24898685eB872b61

Paid supporters receive priority support.

You can also support the project by purchasing DigitalOcean hosting with the Argos Open Tech referral link which helps to offset CDN hosting costs.

License

Dual licensed under either the MIT License or CC0.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.