Skip to main content

A small and fast language identification model powered by fastText

Project description

A simple answer to your language identification needs, powered by fastText. It wraps the language identification model in a small Python package for easier use.


pip install ftlid


from ftlid import identify_language, load_model

# prints 'en'
print(identify_language('Hello, how are you?'))

# prints (['en'], array([0.99987388]))
print(identify_language('Hello, how are you?', with_prob=True))

# prints ['en', 'de']
print(identify_language('And then he said "Ich liebe dich"!', k=2))

# prints (['en', 'de'], array([0.50208992, 0.30427793]))
print(identify_language('And then he said "Ich liebe dich"!', with_prob=True, k=2))

# if you want to use your custom model
print(identify_language('Hello, how are you?', model_path='model.ftz'))

# if you would like to pass the model yourself or prevent it from being loaded on every request
model = load_model('model.ftz')
print(identify_language('Hello, how are you?', model=model))


Licensed under the MIT license (see LICENSE file for more details).

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for ftlid, version 0.1.1
Filename, size File type Python version Upload date Hashes
Filename, size ftlid-0.1.1-py3-none-any.whl (780.1 kB) File type Wheel Python version py3 Upload date Hashes View hashes
Filename, size ftlid-0.1.1.tar.gz (782.3 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page