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.
Install
pip install ftlid
Example
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))
License
Licensed under the MIT license (see LICENSE file for more details).
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ftlid-0.1.2.tar.gz
(782.3 kB
view hashes)
Built Distribution
ftlid-0.1.2-py3-none-any.whl
(780.1 kB
view hashes)