neural-networks

AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.

Speech Recognition model based off of FAIR research paper built using Pytorch.

A PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.

Implementation of deep implicit attention in PyTorch

Generate Cartoon Images using Generative Adversarial Network

🤖 Python implementations of some of the fundamental Machine Learning models and algorithms from scratch with interactive Jupyter demos and math being explained.

Implementation of the premier Text to Video model from OpenAI

Code for Deep Learning for Modern AI

Free AI/ML course with 950+ Jupyter notebooks — Python, deep learning, LLMs, RAG, agents, prompt engineering, fine-tuning, MLOps

A collection of AI/ML articles, guides and projects.

Physics-inspired transformer modules based on mean-field dynamics of vector-spin models in JAX

This repository contain my 75Day Hard Generative AI and LLM Learning Challenge.

A PyTorch implementation of DeepSpeech and DeepSpeech2.

Code and Data for Text Classification of AI Related Patents Research Paper

APDTFlow is a modern and extensible forecasting framework for time series data that leverages advanced techniques including neural ordinary differential equations (Neural ODEs), transformer-based components, and probabilistic modeling. Its modular design allows researchers and practitioners to experiment with multiple forecasting models and easily

An end-to-end image captioning project using a CNN encoder (ResNet-50) and LSTM decoder in PyTorch. Includes vocabulary building, preprocessing, training with BLEU evaluation, and inference. Generates natural language captions for images with saved metrics, model checkpoints, and visualization outputs.

Run Vision LLMs, TTS and STT APIs. Website and API for https://text-generator.io

A tool to streamline AI image captioning

Train transformer-based models.

Easy to use Multi-Provider ASR/Speech To Text and NLP engine