deep-translator
Translation for humans
A flexible FREE and UNLIMITED tool to translate between different languages in a simple way using multiple translators.
- Free software: MIT license
- Documentation: https://deep-translator.readthedocs.io.
Motivation
I needed to translate a text using python. It was hard to find a simple way to do it. There are other libraries that can be used for this task, but most of them are buggy, not free, limited, not supported anymore or complex to use.
Therefore, I decided to build this simple tool. It is 100% free, unlimited, easy to use and provide support for all languages.
Basically, my goal was to integrate support for multiple famous translators in this tool.
When you should use it
- If you want to translate text using python
- If you want to translate from a file
- If you want to get translations from many sources and not only one
- If you want to automate translations
- If you want to compare different translations
- If you want to detect language automatically
Why you should use it
- It's the only python tool that integrates many translators
- multi language support
- supports batch translation
- High level of abstraction
- Automatic language detection
- Easy to use and extend
- Support for most famous universal translators
- Stable and maintained regularly
Features
- Support for google translate
- Support for Pons translator
- Support for the Linguee translator
- Support for the Mymemory translator
- Support for the Yandex translator (version >= 1.2.1)
- Support for the QCRI translator (version >= 1.2.4)
- Support for the DeepL translator (version >= 1.2.5)
- Automatic single language detection
- Batch language detection
- Translate directly from a text file
- Get multiple translation for a word
- Automate the translation of different paragraphs in different languages
- Translate directly from terminal (version >= 1.1.0)
Installation
Install the stable release:
$ pip install -U deep_translator
take a look at the docs if you want to install from source.
Quick Start
from deep_translator import GoogleTranslator
translated = GoogleTranslator(source='auto', target='de').translate("keep it up, you are awesome") # output -> Weiter so, du bist großartig
or from terminal
$ deep_translator -trans "google" -src "en" -tg "de" -txt "keep it up, you are awesome"
Usage
In this section, demos on how to use all different integrated translators in this tool are provided.
Note
You can always pass the languages by the name or by abbreviation.
Example: If you want to use english as a source or target language, you can pass english or en as an argument
Imports
from deep_translator import (GoogleTranslator,
PonsTranslator,
LingueeTranslator,
MyMemoryTranslator,
YandexTranslator,
DeepL,
QCRI,
single_detection,
batch_detection)
Check Supported Languages
Note
You can check the supported languages of each translator by calling the get_supported_languages function as a static method.
# default return type is a list
langs_list = GoogleTranslator.get_supported_languages() # output: [arabic, french, english etc...]
# alternatively, you can the dictionary containing languages mapped to their abbreviation
langs_dict = GoogleTranslator.get_supported_languages(as_dict=True) # output: {arabic: ar, french: fr, english:en etc...}
Language Detection
Note
You can also detect language automatically. Notice that this package is free and my goal is to keep it free. Therefore, you will need to get your own api_key if you want to use the language detection function. I figured out you can get one for free here: https://detectlanguage.com/documentation
- Single Text Detection
lang = single_detection('bonjour la vie', api_key='your_api_key')
print(lang) # output: fr
- Batch Detection
lang = batch_detection(['bonjour la vie', 'hello world'], api_key='your_api_key')
print(lang) # output: [fr, en]
Google Translate
text = 'happy coding'
- You can use automatic language detection to detect the source language:
translated = GoogleTranslator(source='auto', target='de').translate(text=text)
- You can pass languages by name or by abbreviation:
translated = GoogleTranslator(source='auto', target='german').translate(text=text)
# Alternatively, you can pass languages by their abbreviation:
translated = GoogleTranslator(source='en', target='de').translate(text=text)
- Translate batch of texts
texts = ["hallo welt", "guten morgen"]
# the translate_sentences function is deprecated, use the translate_batch function instead
translated = GoogleTranslator('de', 'en').translate_batch(texts)
- Translate from a file:
translated = GoogleTranslator(source='auto', target='german').translate_file('path/to/file')
Mymemory Translator
Note
As in google translate, you can use the automatic language detection with mymemory by using "auto" as an argument for the source language. However, this feature in the mymemory translator is not so powerful as in google translate.
- Simple translation
text = 'Keep it up. You are awesome'
translated = MyMemoryTranslator(source='auto', target='french').translate(text)
- Translate batch of texts
texts = ["hallo welt", "guten morgen"]
# the translate_sentences function is deprecated, use the translate_batch function instead
translated = MyMemoryTranslator('de', 'en').translate_batch(texts)
- Translate from file
path = "your_file.txt"
translated = MyMemoryTranslator(source='en', target='fr').translate_file(path)
DeepL Translator
Note
In order to use the DeepL translator, you need to generate an api key. Visit https://www.deepl.com/en/docs-api/ for more information
- Simple translation
text = 'Keep it up. You are awesome'
translated = DeepL("your_api_key").translate(text)
- Translate batch of texts
texts = ["hallo welt", "guten morgen"]
# the translate_sentences function is deprecated, use the translate_batch function instead
translated = DeepL("your_api_key").translate_batch(texts)
QCRI Translator
Note
In order to use the QCRI translator, you need to generate a free api key. Visit https://mt.qcri.org/api/ for more information
- Check languages
# as a property
print("language pairs: ", QCRI("your_api_key").languages)
- Check domains
# as a property
print("domains: ", QCRI("your_api_key").domains)
- Text translation
text = 'Education is great'
translated = QCRI("your_api_key").translate(source='en', target='ar', domain="news", text=text)
# output -> التعليم هو عظيم
# see docs for batch translation and more.
Linguee Translator
word = 'good'
- Simple Translation
translated_word = LingueeTranslator(source='english', target='french').translate(word)
# pass language by their abbreviation
translated_word = LingueeTranslator(source='en', target='fr').translate(word)
- Return all synonyms or words that matches
# set the argument return_all to True if you want to get all synonyms of the word to translate
translated_word = LingueeTranslator(source='english', target='french').translate(word, return_all=True)
- Translate a batch of words
translated_words = LingueeTranslator(source='english', target='french').translate_words(["good", "awesome"])
PONS Translator
Note
You can pass the languages by the name or by abbreviation just like previous examples using GoogleTranslate
word = 'awesome'
- Simple Translation
translated_word = PonsTranslator(source='english', target='french').translate(word)
# pass language by their abbreviation
translated_word = PonsTranslator(source='en', target='fr').translate(word)
- Return all synonyms or words that matches
# set the argument return_all to True if you want to get all synonyms of the word to translate
translated_word = PonsTranslator(source='english', target='french').translate(word, return_all=True)
- Translate a batch of words
translated_words = LingueeTranslator(source='english', target='french').translate_words(["good", "awesome"])
Yandex Translator
Note
You need to require an private api key if you want to use the yandex translator. visit the official website for more information about how to get one
- Language detection
lang = YandexTranslator('your_api_key').detect('Hallo, Welt')
print(f"language detected: {lang}") # output -> language detected: 'de'
- Text translation
# with auto detection | meaning provide only the target language and let yandex detect the source
translated = YandexTranslator('your_api_key').translate(source="auto", target="en", text='Hallo, Welt')
print(f"translated text: {translated}") # output -> translated text: Hello world
# provide source and target language explicitly
translated = YandexTranslator('your_api_key').translate(source="de", target="en", text='Hallo, Welt')
print(f"translated text: {translated}") # output -> translated text: Hello world
- File translation
translated = YandexTranslator('your_api_key').translate_file(source="auto", target="en", path="path_to_your_file")
- Batch translation
translated = YandexTranslator('your_api_key').translate_batch(source="auto", target="de", batch=["hello world", "happy coding"])
Usage from Terminal
For a quick access, you can use the deep_translator from terminal. For this to work, you need to provide the right arguments, which are the translator you want to use, source language, target language and the text you want to translate.
For example, provide "google" as an argument to use the google translator. Alternatively you can use the other supported translators. Just read the documentation to have an overview about the supported translators in this library.
$ deep_translator --translator "google" --source "english" --target "german" --text "happy coding"
Or you can go for the short version:
$ deep_translator -trans "google" -src "english" -tg "german" -txt "happy coding"
If you want, you can also pass the source and target language by their abbreviation
$ deep_translator -trans "google" -src "en" -tg "de" -txt "happy coding"
Tests
- Install dev requirements
$ pip install -r requirements_dev.txt
- Or just install pytest
$ pip install pytest
- you can run tests individually for each translator by passing the prefix test_ followed by the translator name as an argument to pytest.
$ pytest test_google_trans
$ pytest test_linguee
$ pytest test_mymemory
$ pytest test_pons
- Alternatively, you can run the test suite
$ pytest -ra
Links
Check this article on medium to know why you should use the deep-translator package and how to translate text using python. https://medium.com/@nidhalbacc/how-to-translate-text-with-python-9d203139dcf5
Next Steps
Take a look in the examples folder for more :) Contributions are always welcome. Read the Contribution guildlines Here
The Translator++ mobile app
After developing the deep_translator, I realised how cool this would be if I can use it as an app on my mobile phone. Sure, there is google translate, pons and linguee apps etc.. but isn't it cooler to make an app where all these translators are integrated?
Long story short, I started working on the app. I decided to use the kivy framework since I wanted to code in python and to develop a cross platform app. I open sourced the Translator++ app on my github too. Feel free to take a look at the code or make a pull request ;)
Note
The Translator++ app is based on the deep_translator package. I just built the app to prove the capabilities of the deep_translator package ;)
I published the first release on google play store on 02-08-2020
Here are some screenshots:
- Phone
- Tablet: