avidale/encodechka
The tiniest sentence encoder for Russian language
This project helps Russian-speaking developers and data scientists find the most efficient sentence embedding models. It takes various Russian text encoder models and evaluates how well they convert short texts into meaningful numerical representations (vectors). The output is a leaderboard ranking these models based on both their quality and processing speed.
246 stars. No commits in the last 6 months.
Use this if you need to choose a fast and accurate model to embed Russian sentences for applications like search, recommendation systems, or text classification.
Not ideal if your primary concern is broad coverage of diverse NLP tasks like question answering or summarization, for which ruMTEB might be a better fit.
Stars
246
Forks
13
Language
Python
License
MIT
Category
Last pushed
Jul 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/avidale/encodechka"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
isaacus-dev/semchunk
A fast, lightweight and easy-to-use Python library for splitting text into semantically...
chatopera/Synonyms
:herb: 中文近义词：聊天机器人，智能问答工具包
CUNY-CL/wikipron
Massively multilingual pronunciation mining
jacksonllee/pylangacq
Language Acquisition Research Tools
goodmami/wn
A modern, interlingual wordnet interface for Python