Nijat Zeynalov's repositories
image_to_handwriting_az
This project allows you to convert image into Azerbaijani handwriting
Satellite-images-to-real-maps-with-Deep-Learning
In this project, I developed a Pix2Pix generative adversarial network for image-to-image translation. I have used the so-called maps dataset used in the Pix2Pix paper.
New-product-demand-forecasting-via-Content-based-learning-for-multi-branch-stores
New product demand forecasting via Content based learning for multi-branch stores: Ali and Nino Use Case
mgpt-az-streamlit
This project is a Streamlit app that uses the mGPT-XL (1.3B) model to generate Azerbaijani text. Users can input partial text, and the model will complete it with contextually relevant text in Azerbaijani.
automate-web-scraping-send-whatsapp-alert-with-aws
Scraping Azerbaijani real estate website and sending whatsapp message with AWS Lambda function that automatically triggered by Amazon CloudWatch.
Norvig-s-Spell-Checker-Algorithm-for-Azerbaijani-Language
The purpose of this project is to prepare a spell checker for Azerbaijani language by implementing a Azerbaijani corpus to Norvig’s algorithm. The corpus I created consists of 1478667 words collected from 47 books in 6 fields (biology, geography, detective, literature, encyclopedia, novel)
advanced-hyperparameter-optimization-techniques
HalvingGridSearch, HalvingRandomSearch, Bayesian Optimization, Keras Tuner, Hyperband optimization
AzVoiceSent
AzVoiceSent is research project focused on sentiment classification from voice transcriptions in Azerbaijani. The project has the potential to provide valuable insights into the sentiment expressed by speakers in various domains and applications.
azcorpus_v0
azcorpus - The largest NLP corpus for Azerbaijani (1.9M documents, ~ 18M sentences)
Easy-Recipes-bot
This telegram bot will find easy recipes in Azerbaijani using ingredients you already have in the kitchen.
experimenteer
Automate your classic machine learning experiments with experimenteer.
concept-drift-adversarial-validation
In the project, I have detected concept drift by using adversarial validation and Kolmogorov-Smirnov test which can also be used in the deployed system.
Detecting-Weapon-objects-by-using-RetinaNet-model-with-TensorFlow
I have used Object Detection API and retrain RetinaNet model to spot weapon objects using just 4 training images.
Generate-Synthetic-Images-with-DCGANs-in-Keras
Generate images of clothing items by using Deep Convolutional Generative Adversarial Networks (DCGANs)
mT5-based-azerbaijani-news-summarize
mT5-small based Azerbaijani News Summarization
session-based-recommender-supermarket
Session-based Recommendation System for Supermarket Context
azerbaijani-medical-question-classification
Azerbaijani Medical Forum Question Classification
Building-Neural-Network-architectures-from-scratch
I have built simple versions of some Neural Network architectures (Alexnet, Inception-v1, Resnet-18, Vgg-16) from scratch by using TensorFlow.
DEEP-LEARNING-FOR-SENTIMENT-ANALYSIS-ON-REVIEWS-OF-MODERN-AZERBAIJANI-MOVIES
The paper mainly describes the implementation of the Multilayer Perceptron (MLP) model - that can be used to detect sentiments from the text.
handling-imbalanced-data
An imbalanced classification problem is a problem that involves predicting a class label where the distribution of class labels in the training dataset is not equal.
optuna-hyperparameter-optimization
Optuna is an open-source hyperparameter optimization framework to automate hyperparameter search. The key features of Optuna include automated search for optimal hyperparameters, efficiently search large spaces and prune unpromising trials for faster results, and parallelize hyperparameter searches over multiple threads or processes.
Advanced-eXtreme-Gradient-Boosting-with-Python
Developing, evaluating and monitoring popular XGBoost model.
azerbaijani-multi-news-dataset
Azerbaijani News Summary Dataset
finetuning-large-mms-1b-azerbaijani-common_voice15.0
This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_15_0 dataset.
OpenVoice
Instant voice cloning by MyShell.
portfolio
My portfolio website with built-in blogs and courses support
Scikit-Optimize-Bayesian-Hyperparameter-Optimization
Scikit Optimize implements several methods for sequential model-based optimization. The library is very easy to use and provides a general toolkit for Bayesian optimization that can be used for hyperparameter tuning. It also provides support for tuning the hyperparameters of machine learning algorithms offered by the scikit-learn library.
Whole-or-Damaged-car
Convolutional Neural Network with a custom architecture used for binary classification of images. The model predicts whether the car is a whole or a damaged.