We are happy to announce the release of version 0.9.2.
WebAssembly
We are excited to release fastText bindings for WebAssembly. Classification tasks are widely used in web applications and we believe giving access to the complete fastText API from the browser will notably help our community to build nice tools. See our documentation to learn more.
Autotune: automatic hyperparameter optimization
Finding the best hyperparameters is crucial for building efficient models. However, searching the best hyperparameters manually is difficult. This release includes the autotune feature that allows you to find automatically the best hyperparameters for your dataset.
You can find more information on how to use it here.
Python
fastText loves Python. In this release, we have:
- several bug fixes for prediction functions
- nearest neighbors and analogies for Python
- a memory leak fix
- website tutorials with Python examples
The autotune feature is fully integrated with our Python API. This allows us to have a more stable autotune optimization loop from Python and to synchronize the best hyper-parameters with the _FastText model object.
Pre-trained models tool
We release two helper scripts:
- download_model.py to automatically download pre-trained vectors from our website
- reduce_model.py to reduce the word-vectors' size using PCA.
They can also be used directly from our Python API.
More metrics
When you test a trained model, you can now have more detailed results for the precision/recall metrics of a specific label or all labels.
Paper source code
This release contains the source code of the unsupervised multilingual alignment paper.
Community feedback and contributions
We want to thank our community for giving us feedback on Facebook and on GitHub.