A Python package that combines shadow removal preprocessing with state-of-the-art OCR for accurate handwriting transcription. The package offers both local inference using MiniCPM-V and cloud-based…

Tenacious tool calling built on LangGraph

A fast multimodal LLM for real-time voice

first base model for full-duplex conversational audio

Blazing fast whisper turbo for ASR (speech-to-text) tasks

📝 Generate personalized writing content

An open-source implementaion for fine-tuning Molmo-7B-D and Molmo-7B-O by allenai.

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

Chat with Hacker News using natural language. Built with OpenAI Functions and Vercel AI SDK.

DocLing: Multilingual Document Understanding

Speech To Speech: an effort for an open-sourced and modular GPT4-o

Build your own generative UI chatbot using the Vercel AI SDK and Google Gemini

This is the Placeholder for Whisper Model Finetune

FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Python scraper based on AI

Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript

Interview Prep

An app for finger vein scanning device management and authentication

This repository contains demos I made with the Transformers library by HuggingFace.

Implementation of Prompt-to-Prompt Image Editing with Cross Attention Control

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.