Sign inDemoInstall


Package Overview
File Explorer

Install Socket

Detect and block malicious and high-risk dependencies



A set of tools to compress gensim fasttext models




This Python 3 package allows to compress fastText word embedding models (from the gensim package) by orders of magnitude, without significantly affecting their quality.

Here are some links to the models that have already been compressed.

This blogpost in Russian and this one in English give more details about the motivation and methods for compressing fastText models.

Note: gensim==4.0.0 has introduced some backward-incompatible changes:

  • With gensim<4.0.0, please use compress-fasttext<=0.0.7 (and optionally Russian models from our first release).
  • With gensim>=4.0.0, please use compress-fasttext>=0.1.0 (and optionally Russian or English models from our 0.1.0 release).
  • Some models are no longer supported in the new version of gensim+compress-fasttext (for example, multiple models from RusVectores that use compatible_hash=False).
  • For any particular model, compatibility should be determined experimentally. If you notice any strange behaviour, please report in the Github issues.

The package can be installed with pip:

pip install compress-fasttext[full]

If you are not going to perform matrix decomposition or quantization, you can install a variety with less dependencies:

pip install compress-fasttext

Model compression

You can use this package to compress your own fastText model (or one downloaded e.g. from RusVectores):

Compress a model in Gensim format:

import gensim
import compress_fasttext
big_model = gensim.models.fasttext.FastTextKeyedVectors.load('path-to-original-model')
small_model = compress_fasttext.prune_ft_freq(big_model, pq=True)'path-to-new-model')

Import a model in Facebook original format and compress it:

from gensim.models.fasttext import load_facebook_model
import compress_fasttext
big_model = load_facebook_model('path-to-original-model').wv
small_model = compress_fasttext.prune_ft_freq(big_model, pq=True)'path-to-new-model')

To perform this compression, you will need to pip install gensim==3.8.3 sklearn beforehand.

Different compression methods include:

  • matrix decomposition (svd_ft)
  • product quantization (quantize_ft)
  • optimization of feature hashing (prune_ft)
  • feature selection (prune_ft_freq)

The recommended approach is combination of feature selection and quantization (prune_ft_freq with pq=True).

Model usage

If you just need a tiny fastText model for Russian, you can download this 21-megabyte model. It's a compressed version of geowac_tokens_none_fasttextskipgram_300_5_2020 model from RusVectores.

If compress-fasttext is already installed, you can download and use this tiny model

import compress_fasttext
small_model = compress_fasttext.models.CompressedFastTextKeyedVectors.load(
# [ 0.26762889  0.35489027 ...  -0.06149674] # a 300-dimensional vector
# [('кот', 0.7391024827957153), ('пес', 0.7388300895690918), ('малыш', 0.7280327081680298), ... ]

The class CompressedFastTextKeyedVectors inherits from gensim.models.fasttext.FastTextKeyedVectors, but makes a few additional optimizations.

For English, you can use this tiny model, obtained by compressing the model by Facebook.

import compress_fasttext
small_model = compress_fasttext.models.CompressedFastTextKeyedVectors.load(
# [ 1.84736611e-01  6.32683930e-03  4.43901886e-03 ... -2.88431027e-02]  # a 300-dimensional vector
# [('PHP', 0.5252903699874878), ('.NET', 0.5027452707290649), ('Java', 0.4897131323814392),  ... ]

More compressed models for 101 various languages can be found at

Example of application

In practical applications, you usually feed fastText embeddings to some other model. The class FastTextTransformer uses the scikit-learn interface and represents a text as the average of the embedding of its words. With it you can, for example, train a classifier on top of fastText to tell edible things from inedible ones:

import compress_fasttext
from sklearn.pipeline import make_pipeline
from sklearn.linear_model import LogisticRegression
from compress_fasttext.feature_extraction import FastTextTransformer

small_model = compress_fasttext.models.CompressedFastTextKeyedVectors.load(

classifier = make_pipeline(
    ['banana', 'soup', 'burger', 'car', 'tree', 'city'],
    [1, 1, 1, 0, 0, 0]
classifier.predict(['jet', 'train', 'cake', 'apple'])
# array([0, 0, 1, 1])


This code is heavily based on the navec package by Alexander Kukushkin and the blogpost by Andrey Vasnetsov about shrinking fastText embeddings.


Did you know?

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.


Related posts

SocketSocket SOC 2 Logo


  • Package Alerts
  • Integrations
  • Docs
  • Pricing
  • FAQ
  • Roadmap

Stay in touch

Get open source security insights delivered straight into your inbox.

  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc