AigizK

bashkort-parallel-corpora

bashkort_translate_bot

bashspell

ReadingPipeline

Text reading pipeline that combines segmentation and OCR-models.

video_diarization

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

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

GarbageDetector

GigaAM

Foundational Model for Speech Recognition Tasks

hackaton_irkuts

hunspell

The most popular spellchecking library.

kod_odin

kokoro-voice-composer-backup

Since the owner of the repo took it down and it used an MIT license, I guess it's okay to upload it here for people to use.

lighteval

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

logistic-hackathon-public

MB-iSTFT-VITS2

Application of MB-iSTFT-VITS components to vits2_pytorch

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

piper1-gpl

Fast and local neural text-to-speech engine

qald_9_plus

QALD-9-Plus Dataset for Knowledge Graph Question Answering

RAG-Challenge-2

Implementation of my RAG system that won all categories in Enterprise RAG Challenge 2

SEGM-model

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

Tinkoff.AI-Speech-Meetup-3

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