Metadata-Version: 2.1
Name: fasttext-predict
Version: 0.9.2.4
Summary: fasttext with wheels and no external dependency, but only the predict method (<1MB)
Home-page: https://github.com/searxng/fasttext-predict/
Author: Alexandre Flament
Author-email: alex.andre@al-f.net
License: MIT
Keywords: fasttext,language detection,language identification
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development
Classifier: Topic :: Scientific/Engineering
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX
Classifier: Operating System :: Unix
Classifier: Operating System :: MacOS
License-File: LICENSE

fasttext-predict
================

Python package for
`fasttext <https://github.com/facebookresearch/fastText>`__:

-  keep only the ``predict`` method, all other features are removed
-  standalone package without external dependency (numpy is not a
   dependency)
-  wheels for various architectures using GitHub workflows. The script
   is inspired by lxml build scripts.

Usage
-----

.. code:: sh

   pip install fasttext-predict

.. code:: python

   import fasttext
   model = fasttext.load_model('lid.176.ftz')
   result = model.predict('Fondant au chocolat et tarte aux myrtilles')

See https://fasttext.cc/docs/en/language-identification.html
