averkij Goto Github PK

multipunct

Train punctuation and capitalization models for different languages

nlp

NLP stuff — datasets, tools, etc.

nlp-course-projects

Projects from students of NLP Course

nlp-map

Visualization of the multilingual language models

nn-zero-to-hero

Neural Networks: Zero to Hero

ocr-transformer

OCR seq2seq resnet+transformer

prince

Little Prince. Lingtrain transformer parallel book.

pyctcdecode

A fast and lightweight python-based CTC beam search decoder for speech recognition.

razdel

Rule-based token, sentence segmentation for Russian language

ru-dolph

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

sheckley

Sheckley (Lingtrain Transformer Book)

stanford-cs-229-machine-learning

VIP cheatsheets for Stanford's CS 229 Machine Learning

svoyak

Whisper transcriptions of Russian Jeopardy

tape-benchmark-web

TAPE:

tatoeba-challenge

text-alignment-pipeline

transformer-deploy

Efficient, scalable and enterprise-grade CPU/GPU inference server for Hugging Face transformer models 🚀

tuning_playbook_ru

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

uwsgi-nginx-flask-docker

Docker image with uWSGI and Nginx for Flask applications in Python running in a single container. Optionally with Alpine Linux.

video-splitter

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

vue-dotnet-docker

Minimal boilerplate for a web app using Vue and .NET 5 packed in docker.

woland

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

word-to-number-russian

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