Stars
Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs,…
Guitar Effect Pedal for Raspberry Pi, with a web interface designed specifically for phones.
Raspberry Pi guitar pedal using neural networks to emulate real amps and effects.
Easily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM!
An implementation of PSGD Kron second-order optimizer for PyTorch
Get your documents ready for gen AI
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
Docsifer is a powerful tool for converting various data formats into Markdown for applications such as indexing, text analysis, and more. It supports PDF, PowerPoint, Word, Excel, Images, Audio, HT…
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Metrics for evaluating music and audio generative models – with a focus on long-form, full-band, and stereo generations.
Deploys An Ubuntu Virtual Machine with Docker and Docker Compose Installed in GCP using Terraform
An open-source RAG-based tool for chatting with your documents.
Bare metal to production ready in mins; your own fly server on your VPS.
Encode and decode audio samples to/from compressed latent representations!
A lightweight yet powerful audio-to-MIDI converter with pitch bend detection
Docker image with Uvicorn managed by Gunicorn for high-performance FastAPI web applications in Python with performance auto-tuning.
Set up your own IPsec VPN server in just a few minutes, with IPsec/L2TP, Cisco IPsec and IKEv2. Supports Ubuntu, Debian, CentOS/RHEL, Amazon Linux, Alpine and Raspberry Pi. Includes client config a…
📚 LookScanned.io - Make your PDFs look scanned
A More Fair and Comprehensive Comparison between KAN and MLP
Ratatouille is a Neural Model loader and mixer for Linux/Windows
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models
Convert PDF to markdown + JSON quickly with high accuracy
🐍 Geometric Computer Vision Library for Spatial AI
Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.
Data release for the ImageInWords (IIW) paper.