Sergei Averkiev

Elite
@averkij

ML Engineer. Eager to learn languages, science and engineering.

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

297

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

153

mstu-nlp-course. ML Course created for Bauman Moscow State Technical University

66

top_papers. Top ML papers of the week.

46

lingtrain-aligner-editor. Extracts parallel corpora from the 2 raw texts in different languages.

37

multipunct. Train punctuation and capitalization models for different languages

26

chatgpt-tools. Scripts and stuff

17

Word-to-Number-Russian. Проект для перевода чисел, записанных в текстовом виде на русском языке.

11

docker-flask-vue-boilerplate. The template to pack your Flask + Vue web app.

10

text-alignment-pipeline. Jupyter Notebook

9

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

8

nlp-map. Visualization of the multilingual language models

8

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

7

ml-bootcamp-zh-ru-baseline. ML Bootcamp Machine Translation competition (Chinese to Russian).

6

karcaps. Andrey Karpathy nn-zero-to-hero lectures captions

4

ml-examples. Machine learning training examples

4

prince. Little Prince. Lingtrain transformer parallel book.

2

lingtrain-homepage. Homepage

2

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

2

1984. George Orwell - 1984 (Lingtrain Transformer Book)

2

kek-2023. Some kek

1

lico-udmurt. Udmurt language related materials

1

averkij. Profile repo

1

nlp. NLP stuff — datasets, tools, etc.

1

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

1

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

1

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

1
27
Apply