GitHub - lingvanex-mt/models: Free and open source pre-trained translation models, including Kurdish, Samoan, Xhosa, Lao, Corsican, Cebuano, Galician, Russian, Belarusian and Yoruba.

Lingvanex Translator

Free and Open Source Machine Translation Models in 12 languages, entirely self-hosted. Unlike other APIs, it doesn't rely on proprietary providers such as Google or AWS to perform translations. Instead, its translation engine is powered by the open source CTranslate2 library.

Also we have translation models for 100 other languages. Contact us info@lingvanex.com

Try it online! | API Docs

Free Language Translation Models for CTranslate2

The models support the following languages:

The models are available for download and you can use them in your projects. You can easily run them in your Python environment as shown below.

Requirements

To run the models, you need to install ctranslate2 and sentencepiece:

pip install ctranslate2 sentencepiece

Simple Usage Example

The following code demonstrates how to load and use a model for translation from English to Kurdish (en → ku).

import sentencepiece as spm
from ctranslate2 import Translator

path_to_model = <here_is_your_path_to_the_model>
source = 'en'
target = 'ku'

translator = Translator(path_to_model, compute_type='int8')
source_tokenizer = spm.SentencePieceProcessor(f'{path_to_model}/{source}.spm.model')
target_tokenizer = spm.SentencePieceProcessor(f'{path_to_model}/{target}.spm.model')

text = [
  'I need to make a phone call.',
  'Can I help you prepare food?',
  'We want to go for a walk.'
]

input_tokens = source_tokenizer.EncodeAsPieces(text)
translator_output = translator.translate_batch(
  input_tokens,
  batch_type='tokens',
  beam_size=2,
  max_input_length=0,
  max_decoding_length=256
)

output_tokens = [item.hypotheses[0] for item in translator_output]
translation = target_tokenizer.DecodePieces(output_tokens)
print('\n'.join(translation))

API Usage Examples

Simple

Request:

const url = 'https://api-b2b.backenster.com/b1/api/v3/translate';
const options = {
  method: 'POST',
  headers: {
    accept: 'application/json',
    'content-type': 'application/json',
    Authorization: 'API Key'
  },
  body: JSON.stringify({
      platform: 'api',
      from: 'en', 
      to: 'es',
      data: 'Hello'
    })
};

fetch(url, options)
  .then(res => res.json())
  .then(json => console.log(json))
  .catch(err => console.error(err));

Response:

{
  "err": null,
  "result": "Hola"
}

List of language codes: https://docs.lingvanex.com/reference/user-guide

Auto Detect Language

Request:

const url = 'https://api-b2b.backenster.com/b1/api/v3/translate';
const options = {
  method: 'POST',
  headers: {
    accept: 'application/json',
    'content-type': 'application/json',
    Authorization: 'API Key'
  },
  body: JSON.stringify({
      platform: 'api',
      to: 'en',
      data: 'Auf Wiedersehen'
    })
};

fetch(url, options)
  .then(res => res.json())
  .then(json => console.log(json))
  .catch(err => console.error(err));

Response:

{
  "err": null,
  "result": "Goodbye",
  "from": "de"
}

HTML

Request:

const url = 'https://api-b2b.backenster.com/b1/api/v3/translate';
const options = {
  method: 'POST',
  headers: {
    accept: 'application/json',
    'content-type': 'application/json',
    Authorization: 'API Key'
  },
  body: JSON.stringify({
      platform: 'api',
      translateMode: 'html',
      from: 'en', 
      to: 'es',
      data: '<h1>Welcome to the test page</h1>'
    })
};

fetch(url, options)
  .then(res => res.json())
  .then(json => console.log(json))
  .catch(err => console.error(err));

Response:

{
  "err": null,
  "result": "<h1>Bienvenido a la página de prueba</h1>"
}

Transliteration

Request:

const url = 'https://api-b2b.backenster.com/b1/api/v3/translate';
const options = {
  method: 'POST',
  headers: {
    accept: 'application/json',
    'content-type': 'application/json',
    Authorization: 'API Key'
  },
  body: JSON.stringify({
      platform: 'api',
      from: 'en', 
      to: 'zh-Hans_CN',
      data: 'Hello',
      enableTransliteration: true
    })
};

fetch(url, options)
  .then(res => res.json())
  .then(json => console.log(json))
  .catch(err => console.error(err));

Response:

{
  "err": null,
  "result": "你好",
  "sourceTransliteration": "Hello",
  "targetTransliteration": "Ni Hao"
}

Usage Examples in Different Languages

You can use the Lingvanex API using the following different languages:

Desktop Apps

Translator for MacOS that uses the Lingvanex API.
Translator for Windows that uses the Lingvanex API.

Mobile Apps

Lingvanex Translator is an Android and iOS apps available on the Play Store and available on the App Store that uses the Lingvanex API.
Phone Call Translator is an Android and iOS apps available on the Play Store and available on the App Store that uses the Lingvanex API.

Web Browser

Translator for Browser is a web extension with integrated Lingvanex support.

Translator Bot for Slack

Translator for Slack is a bot for Slack with integrated Lingvanex support.

License

This project is licensed under the MIT License.

Contact

If you have any questions, just email info@lingvanex.com