"RAG-Anything: All-in-One RAG Framework"
On-device TTS model by Neuphonic
ContextGem: Effortless LLM extraction from documents
This project is a real-time, multilingual voice translator that leverages the power of local AI models for speech-to-text, translation, and text-to-speech. It is designed to be a powerful and flexible tool for anyone who needs to communicate across language barriers.
Load Aspect Models in Python
This project is a real-time, multilingual voice translator that leverages the power of local AI models for speech-to-text, translation, and text-to...
Last updated: 2 days agoA voice-enabled AI assistant that converts MCP (Model Context Protocol) servers into OpenAI API tool format and provides real-time voice interactio...
Last updated: 2 days agoImplementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
Last updated: 2 days agoKotai is a fully local, zero-cost voice assistant that combines the power of Kyutai TTS/STT, LiveKit, and local LLMs to create natural conversation...
Last updated: 2 days agoA Docker-based OpenAI-compatible Text-to-Speech API server powered by Kyutai's TTS models with GPU acceleration support.
Last updated: 2 days agoA FastAPI-based Speech-to-Text service that provides OpenAI Whisper API compatibility using Kyutai's powerful STT models. This allows you to use an...
Last updated: 2 days agopix2tex: Using a ViT to convert images of equations into LaTeX code.
Last updated: 2 days agoPython library for working with the QUDT (Quantity, Unit, Dimension and Type) ontology.
Last updated: 2 days ago