ISSAI

TurkicASR

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

TurkicTTS

A multilingual text-to-speech synthesis system for ten lower-resourced Turkic languages: Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Turkmen, Uyghur, and Uzbek.

thermal-facial-landmarks-detection

SF-TL54: Thermal Facial Landmark Dataset with Visual Pairs.

KazEmoTTS

An open-source Kazakh Emotional Text-to-Speech Dataset

telegram-bot-chatgpt

Telegram bot to interact with ChatGPT via voice messages

Central-Asian-Food-Dataset

42 food classes from Kazakh National and Central Asian cuisine

OpenThermalPose

An Open-Source Annotated Thermal Human Pose Dataset and Initial YOLOv8-Pose Baselines

faces-in-event-streams

This repo contains code and instructions for the detection of faces in event streams

Kazakh-Speech-Commands-Dataset

Kazakh Speech Commands Dataset

Soyle

AnyFace

Input-Agnostic Face Detection

KazQAD

An open-source Kazakh Question Answering Dataset

KazParC

An open-source parallel corpus for machine translation across Kazakh, English, Russian, and Turkish

KazSAnDRA

An open-source Kazakh Sentiment Analysis Dataset of Reviews and Attitudes (KazSAnDRA) and baseline sentiment classification models

COHI-O365

The most diverse in number of images/labels/classes fisheye synthetic dataset with source codes and models. As well as a benchmarking testing real dataset.

Column-Design-Optimization

Column design optimization

Common-Objects-in-Hemispherical-Images-Dataset

39 classes of objects sampled from the MS COCO dataset captured with a hemispherical/fisheye camera

city-identification

This repo contains dataset and models for city classification

city-sustainability-indexes

This repo contains code and models for detecting city sustainability indexes

TatarTTS

TatarTTS: An Open-Source Text-to-Speech Synthesis Dataset for the Tatar Language

Vision-Language-Models-for-Activity-Recognition-and-Abnormality-Detection-for-Elderly

VLM PrismerZ model for recognition of emergency and non-emergneyc situations via vision and language transformers. PrismerZ is directed on understanding the contextual information and completing image captioning and visiom qiestion answering tasks.

docker-flask-api-template

This is docker Flask API template with GPU support. As an example the project has X-Ray disease classificator project in it.

talk-llm

Talk with ChatGPT

unified_multimodal_transformer

.github

ISSAI

AnyFacePP

Enhancing-Ambient-Assisted-Living-with-Multi-Modal-Vision-and-Language-Models

This project is aimed at detecting the abnormal behaviour or emergency cases using vision-language model (VLM), large language model (LLM), human detection model, text-to-speech (TTS) and speech-to-text models (STT). The framework can detect the subtle sings of emergency and actively interact with the user to make an accurate decision.

HPE-depth-fisheye

This project used synthetic data created using Nvidia Omniverse to train a camera-view invariant multi-pose HPE model for depth and fisheye cameras.

serge

A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.

TatarSCR

An Open-Source Speech Commands Dataset for the Tatar Language