averkij

a-studio

Lingtrain Alignment Studio is an ML based app for texts alignment on different languages. It can produce parallel corpora and parallel books.

lingtrain-aligner

Lingtrain Aligner — ML powered library for the accurate texts alignment.

mstu-nlp-course

ML Course created for Bauman Moscow State Technical University

lingtrain-aligner-editor

Extracts parallel corpora from the 2 raw texts in different languages.

chatgpt-tools

Scripts and stuff

Word-to-Number-Russian

Проект для перевода чисел, записанных в текстовом виде на русском языке.

docker-flask-vue-boilerplate

The template to pack your Flask + Vue web app.

text-alignment-pipeline

nlp-map

Visualization of the multilingual language models

margo

Transformer book. Multilingual parallel version of Master and Margarita novel.

woland

Parallel corpora of Bulgakov's 'The Master and Margarita'

karcaps

Andrey Karpathy nn-zero-to-hero lectures captions

1984

George Orwell - 1984 (Lingtrain Transformer Book)

lingtrain-homepage

Homepage

averkij

Profile repo

kek-2023

Some kek

nlp

NLP stuff — datasets, tools, etc.

prince

Little Prince. Lingtrain transformer parallel book.

ru-dolph

RUDOLPH: One Hyper-Tasking Transformer can be creative as DALL-E and GPT-3 and smart as CLIP

tuning_playbook_ru

A playbook for systematically maximizing the performance of deep learning models (Russian edition).

video-splitter

Simple Python script to split video into equal length chunks or chunks of equal size, duration, etc.

agents

LLM Agents

kenlm-10-gram

KenLM: Faster and Smaller Language Model Queries

lamm

Language Model Meter

misc

Misc exps.

nn-zero-to-hero

Neural Networks: Zero to Hero

sheckley

Sheckley (Lingtrain Transformer Book)

svoyak

Whisper transcriptions of Russian Jeopardy

tape-benchmark-web

TAPE:

wikiextractor_math

A tool for extracting plain text from Wikipedia dumps (fork for math formulas fixing)