Sergei Averkiev's Projects
Train punctuation and capitalization models for different languages
NLP stuff — datasets, tools, etc.
Projects from students of NLP Course
Visualization of the multilingual language models
Neural Networks: Zero to Hero
OCR seq2seq resnet+transformer
Little Prince. Lingtrain transformer parallel book.
A fast and lightweight python-based CTC beam search decoder for speech recognition.
Rule-based token, sentence segmentation for Russian language
RUDOLPH: One Hyper-Tasking Transformer can be creative as DALL-E and GPT-3 and smart as CLIP
Sheckley (Lingtrain Transformer Book)
VIP cheatsheets for Stanford's CS 229 Machine Learning
Whisper transcriptions of Russian Jeopardy
TAPE:
Efficient, scalable and enterprise-grade CPU/GPU inference server for Hugging Face transformer models 🚀
A playbook for systematically maximizing the performance of deep learning models (Russian edition).
Docker image with uWSGI and Nginx for Flask applications in Python running in a single container. Optionally with Alpine Linux.
Simple Python script to split video into equal length chunks or chunks of equal size, duration, etc.
Minimal boilerplate for a web app using Vue and .NET 5 packed in docker.
Parallel corpora of Bulgakov's 'The Master and Margarita'
Проект для перевода чисел, записанных в текстовом виде на русском языке.