High-Quality Voice Cloning TTS for 600+ Languages

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

Document Rectification and Illumination Correction using a Patch-based CNN

A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies

"Everything else is just for efficiency." — Karpathy's microgpt benchmarked across scalar autograd, NumPy, and PyTorch (RTX 5080)

Building Segment anything model(SAM) from scratch , component by component

Whisper finetuning

Speech Recognition for Uyghur using Speech transformer

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

DN_SuperBook_PDF_Converter - スキャン書籍 PDF をデジタル書籍並みに大変クリアに読みやすくする AI PDF 高品質化・各種調整ツール

A lightning fast audio upsampler.

A high quality and fast TTS repository

.NET wrapper around Google's PDFium library

Nano vLLM

Library used to deskew a scanned document

Uyghurche Aptomatik Awaz Tonush(Uyghur Automatic Speech Recognition)(ASR)

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

Open Source AI Platform - AI Chat with advanced features that works with every LLM

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.

Get up and running with SAM1,2,3, EfficientSAM, YOLO-World, and other promptable vision models locally.

ONNX export and inference for SAM3.

A modern, cross platform IDE for .NET, built with .NET & Godot

Dictionary words-data and code

[SIGGRAPH Asia 2021] DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning

The best ChatGPT that $100 can buy.