AigizK

bashkort-parallel-corpora

bashkort_translate_bot

500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code

500 AI Machine learning Deep learning Computer vision NLP Projects with code

apertium-bak

Apertium linguistic data for Bashkir

bashspell

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

ddsp

DDSP: Differentiable Digital Signal Processing

deepspeech-notes

DeepSpeechNotes is a note taking app using Mozilla's DeepSpeech technology to transcribe speech into text notes.

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

first-order-model

This repository contains the source code for the paper First Order Motion Model for Image Animation

GarbageDetector

hackaton_irkuts

hunspell

The most popular spellchecking library.

kod_odin

logistic-hackathon-public

MB-iSTFT-VITS2

Application of MB-iSTFT-VITS components to vits2_pytorch

ml-course-hse

Машинное обучение на ФКН ВШЭ

neuro-comma

🇷🇺 Punctuation restoration production-ready model for Russian language 🇷🇺

num2words

Modules to convert numbers to words. 42 --> forty-two

OCR-model

An easy-to-run OCR model pipeline based on CRNN and CTC loss

piper

A fast, local neural text to speech system

qald_9_plus

QALD-9-Plus Dataset for Knowledge Graph Question Answering

ReadingPipeline

Text reading pipeline that combines segmentation and OCR-models.

SEGM-model

An easy-to-run semantic segmentation model based on Unet

spleeter

Deezer source separation library including pretrained models.

STT

🐸STT - a deep learning toolkit for Speech-to-Text, battle-tested in research and production

TurkicASR

A multilingual ASR model that can recognize ten Turkic languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek.

ulyanovsk_championat

vits2_pytorch

unofficial vits2-TTS implementation in pytorch

web_elan