oborchers/Fast_Sentence_Embeddings

Compute Sentence Embeddings Fast!

46
/ 100
Emerging

This tool helps data professionals quickly convert large collections of sentences or documents into numerical 'sentence vectors.' You provide your text data and, optionally, a pre-trained word embedding model, and it outputs these numerical representations. These vectors can then be used for tasks like comparing document similarity, clustering, or as input for other machine learning models. It's designed for data scientists or NLP engineers who need to process text at very high speeds without needing specialized hardware.

625 stars. No commits in the last 6 months.

Use this if you need to generate numerical representations for millions of sentences or documents extremely fast, and existing solutions like sentence transformers or spaCy are too slow or consume too much memory, especially if you cannot use GPUs.

Not ideal if your primary concern is the absolute highest quality of sentence representation and you are not bottlenecked by processing speed or GPU availability.

natural-language-processing document-similarity text-analytics large-scale-text-processing information-retrieval
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

625

Forks

84

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Mar 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/oborchers/Fast_Sentence_Embeddings"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.