Skip to main content

Word Vector Encoder

Project description

# Vectoria A Word Vector Encoder, used to turn word strings into dense numerical embeddings for machine learning models.

## Words and Character Trigrams Both word and chararacter trigram parsings are supported, though readily available GLOVE word vectors do not provide for trigram parsing.

## Model Download The various embedding classes will download and compile dense numpy arrays of word vectors. Allow for 4G of space for each language model. The model files will be cached as additional files within the downloaded and installed python module.

## [FastText]( FastText is a unique word encoding model that combines full words and character ngrams, allowing encodings of unknown words to be estimated by their constituent characters.

And, there are [pretrained vectors]( available for many languages, which means you can get started quickly. This library will download and unpack those pretrained models for you.

Take a look at the `examples` folder.

Project details

Download files

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

Source Distribution

vectoria-0.0.1.tar.gz (6.8 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page