- Cologne, Germany
Stars
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.
antonio-ivanovski / spliit-cloud
Forked from spliit-app/spliitFree and Open Source Alternative to Splitwise. Share expenses with your friends and family.
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
Rust library for whisper.cpp compatible Mel spectrograms
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Implementation of the Wave-U-Net for audio source separation
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
A high-quality speech analysis, manipulation and synthesis system
The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)
This plugin allows users to sign in through an SSO provider (such as Google, Microsoft, or your own provider). This enables one-click signin.
A standalone application for managing LibreChat configurations and permissions
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
A JSON Annotated Music Specification for Reproducible MIR Research
The Harmonix Set: Beats, Downbeats, and Structural Annotations for Pop Music
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
End-to-end encrypted messaging, voice, and video. Entry point that orchestrates every public component.
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
Source code for BeatNet+ training and inference, pre-trained weights, and prepared dataset annotations for rhythm analysis.
High-Quality Voice Cloning TTS for 600+ Languages