Codebase for the implementaion of graph-rag system

LLM inference in C/C++

LaTeX-template for russian Phd thesis

Accentor and transcriptor for Russian language

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

A library to make augmented audio (8/16 kHz, mono, WAV PCM) with noises corpora.

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

A tool for extracting plain text from Wikipedia dumps

VOSK Speech Recognition Toolkit

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

KenLM: Faster and Smaller Language Model Queries

Fast and customizable framework for automatic ML model creation (AutoML)

RuNNE

Second place ShiftsChallenge Weather track solution

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

Tensorflow 2.0 implementation of "Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles" (http://arxiv.org/abs/1612.01474)

Russian sentiment analysis evaluation SentiRuEval-2016

Acoustic model trainer for CMU Sphinx

A small speech recognizer

Bayesian Deep Learning Benchmarks

A simple and fast rule-based sentence segmentation. Tested on OpenCorpora and SynTagRus datasets.

Open STT

deep learning based speech enhancement using keras or pytorch, make it easy to use

Morphological analyzer for Russian and English languages based on neural networks and dictionary-lookup systems.

fast python port of arc90's readability tool, updated to match latest readability.js!