Skip to content
View chappiii's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report chappiii

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
chappiii/README.md

Hi there, I'm Kidus!

Data Scientist

cmatrix_sticker

  • 🎓 MSc in Computer Science at Blekinge Institute of Technology

  • 🌱 I’m currently working on and learning about Graph RAGs.

  • 📫 How to reach me chappi787@gmail.com

Languages and Tools:

python javascript typescript c react docker git html5 mongodb mysql nodejs scikit_learn

Connect with me:

Kidus

Pinned Loading

  1. whisper-Amharic-finetuning whisper-Amharic-finetuning Public

    Fine-tuned OpenAI Whisper (small) for Amharic speech recognition. Trained on Common Voice and FLEURS, achieving 41% WER.

    Python

  2. Alzheimer-Disease-classification Alzheimer-Disease-classification Public

    Comparative analysis of ML models (Random Forest, XGBoost, CatBoost, SVM, and more) for Alzheimer's disease screening, with feature selection, hyperparameter tuning, and gender-based evaluation.

  3. k-mean-clustering--in-C k-mean-clustering--in-C Public

    K-Means clustering algorithm implemented in C, supporting up to 10,000 2D data points with dynamic memory allocation, file I/O, and Valgrind-verified memory management.

    C

  4. RAG-microservice RAG-microservice Public

    A simple RAG system that answers questions about Alice in Wonderland using React, FastAPI, LangChain, ChromaDB, and OpenAI ; containerized with Docker and configured for K8s deployment.

    Python

  5. lstm-financial-anomaly-detection lstm-financial-anomaly-detection Public

    Unsupervised anomaly detection in financial transactions using K-Means, LSTM Autoencoder, and VAE — comparing model effectiveness on 217K unlabeled records

    Jupyter Notebook