KevKibe

African-Whisper

🚀 Framework for seamless fine-tuning of Whisper model on a multi-lingual dataset and deployment to prod.

distil-whisper

Modification of the original distil-Whisper, that supports multi-GPU distillation using DistributedDataParallel.

docindex

⚡️Framework for fast persistent storage of multiple document embeddings and metadata into Pinecone for source-traceable, production-level RAG.

Finetuning-WhisperSmall-LoRA-Swahili

This repository features code for Swahili Automatic Speech Recognition (ASR) fine-tuning using the Whisper model on Swahili Common Voice dataset.

GazeDirection-using-Mediapipe

This project is a Python program that uses the mediapipe and opencv libraries to track the Iris movement of a subject in real-time webcam video stream and calculate the gaze direction of the user.

kaggle-script-action

Run model training and CI/CD workflows on Kaggle kernels with free GPU/TPU resources.

memvectordb

⚡️Lightning fast in-memory VectorDB written in rust🦀

RealTime-Gesture-Recognition-using-Mediapipe

This is a project that showcases finetuning a model and performing gesture recognition of 21 different gestures using Mediapipe from Google.

RealTime-Voice-Translation-using-Whisper

The application allows users to record speech, transcribe it using the Whisper ASR (Automatic Speech Recognition) model, translate the transcribed text into a selected language, and play back the translated text using the Elevenlabs TTS (Text-to-Speech) engine.

Semantic-Image-Segmentation-using-Tensorflow-Keras

Performing a computer vision task, semantic segmentation with the goal of having a model that can identify the different classes of clothings from random images.

KevKibe/Semantic-Image-Segmentation-using-Tensorflow-Keras

Performing a computer vision task, semantic segmentation with the goal of having a model that can identify the different classes of clothings from random images.

KevKibe/Medium-Article-Chatbot

This is an application that allows users to interact with one or many articles from Medium using conversational AI techniques. The chatbot utilizes the OpenAI GPT-3.5 model and provides answers to user queries based on the content of the Medium articles.

KevKibe/Carbon-Dioxide-Prediction-challenge

KevKibe/Credit-Card-Users-Churn-Prediction

A predictive model to identify customers who are at risk of attrition for a credit card service in order to find the key causes that drive attrition. This can help banks take appropriate actions to build better retention policies for customers.

KevKibe/Crop-Forecasting-Challenge

This challenge is to predict the yield of rice crop for a given season at 100 geo locations (latitude and longitude) in the Chau Thanh, Thoai Son and Chau Phu regions of Vietnam using satellite data.

KevKibe/Document-Interaction-using-OpenAI-and-Pinecone

This is an application that allows users to interact with a text, pdf or word document using conversational AI techniques. The chatbot leverages the OpenAI GPT-3.5 model and Pinecone vectore store to deliver responses to user inquiries, utilizing the content of the loaded document.

KevKibe/Fraud-Detection-for-Vehicle-Insurance-Claims

Training and fitting a model that classifies a vehicle insurance claim as either fraudulent or legitimate and deployed as a REST API using Flask and containerized using Docker.

KevKibe/Marble-Surface-Anomaly-Detection-using-CNN-model

This is a Computer Vision task that uses a CNN model to detect tiles with surface anomalies and to classify them as either good or defective.

KevKibe/TimeSeries-Prediction-on-climate-data-using-Deep-Learning

This is an interactive time-series forecasting application on climate data using a deep learning model.

KevKibe/Topic-Modelling-using-LDA

The goal of this project is to perform topic modelling on a dataset of news headlines to show the topics that stand out and uncover patterns and trends in the news

KevKibe/YouTube-Comments-Insights-and-Analytics

This is an application that can easily summarize your comments from specific uploaded YouTube videos and leverage natural language queries for efficient searches. Moreover, harness the power of the YouTube Analytics API v2 to extract insightful analytics data for both your individual uploaded videos and the entire channel.

KevKibe/Audio-MNIST-Digit-Recognition

The objective here is to build an Artificial Neural Network that can look at Mel or MFCC spectrograms of audio files and classify them into 10 classes. The audio files are recordings of different speakers uttering a particular digit and the corresponding class to be predicted is the digit itself.

KevKibe/BigMart-Sales-Prediction

To build a predictive model that can find out the sales of each product at a particular store and then provide actionable recommendations

KevKibe/Chat-based-Interactions-with-Swahili-Audio-and-Videos

This is an application that enables a chat-based conversation in English with Swahili videos/audio files using Python and deployed as a REST API using Flask containerized using Docker.

KevKibe/Data-Professions-Salary-Evaluation-and-Estimation-Project

The project aims to provide a solution for recruiters who struggle with determining appropriate salary ranges to offer candidates, as well as candidates who may be unsure about the salary ranges.

KevKibe/Determining-Target-Market-For-a-VideoGame-Company-using-ML

Lets say there is a video game company being set up and they do not know what global region to market their products to. Using data from past video game sales this problem can be solved.

KevKibe/Document-Summarization-using-NLP-techniques

a project that aims at creating a shorter version of a given text document while retaining the most important information.

KevKibe/Foreground-extraction-webapp-using-DeeplabV3

This repo contains code implementation of foreground extraction/ background removal of images using a pretrained deep learning model DeeplabV3 from Pytorch.

KevKibe/Gender-classification-from-Audio-files-

KevKibe/High-Performance-Image-Generation-using-Stable-Diffusion-in-KerasCV

This is a notebook implementation of a Image generation using Stable Diffusion model in KerasCV using textual prompts and comparing the traditional method and XLA compilation method which achieves faster generation speed.

KevKibe/Hospital-Patient-Length-of-Stay-Prediction

Creating a solution to staff and resource management in hospitals by fitting a model that predicts the length of stay of a patient using data on the patient and illness and deploying the model as a REST API using Flask containerized using Docker.

KevKibe/Image-Segmentation-using-TensorFlow

Perform semantic segmentation to classify each pixel in a cardiac MRI image whether the pixel is a part of the left ventricle (LV) or not.

KevKibe/Inflation_in_Kenya_TimeSeries_Prediction

This is a time-series forecasting application used for predicting future inflation rate in Kenya using Deep Learning.

KevKibe/LSTM-Model-on-Arxiv-Data

This is a project that aims to use an LSTM model to autocomplete titles of some sampled(1000) ML papers in the Arxiv database from the user input.

KevKibe/ML-Interview-Prep

This repository serves as a documentation of interview questions and answers in the field of Machine Learning and Deep Learning that I encounter, along with additional notes.

KevKibe/PLC-Device-Diagnostic-and-Corrective-Action-Prediction

This is an implementation of an LSTM Model used to predict the Diagnostic and Corrective Action of industrial Programming Logic Control(PLC) from a dataset containing that information.

KevKibe/Predicting-Customer-Retention-for-British-Airways

Fitting a model that predicts which customer books with British Airways Airline. This will help to identify the most important features to ensure maximum user retention.

KevKibe/Predicting-Wages

Predict wages of the workers using a linear combination of workers characteristics and assessing the predictive performance of our prediction rules using the Mean Squared Error (MSE), adjusted MSE and r-squared as well as out-of-sample MSE and r-squared.

KevKibe/Restaurant_Review_Sentiment_Analysis_and_AI_Recommendation

A webapp that scrapes reviews from TripAdvisor and performs sentiment analysis to return the split of negative and positive reviews and goes ahead to use AI to give suggestions on dealing with the issues in the negative reviews.

KevKibe/Street-View-Housing-Number-Digit-Recognition-using-ANN-and-CNN

A project to build a feed-forward neural network model and convolution neural network model that can recognize the digits in the images and compare the accuracy.