Orpheus TTS is an open-source system for human-sounding speech synthesis using Llama-3b backbone.
TEN is a real-time, distributed, cloud-edge multimodal AI Agent Framework supporting multiple programming languages.
A collection of benchmarks and datasets for evaluating large language models (LLMs).
Agno is a lightweight library for building Agents with memory, knowledge, tools and reasoning.
Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.
Awesome-RAG-VIsion is a curated repository of advanced retrieval augmented generation techniques for Computer Vision.
Open-source framework for training large language models with a focus on readability and support for various training methods.
A GitHub repository for Vanna, an AI tool for various applications.
EdgePersona is a fully localized intelligent digital human that runs offline with low computational requirements.
A General-Purpose AI Agent that bridges insight with execution, helping users move from idea to results effortlessly.
A batch processing tool for GPT-4o that allows users to create and manage tasks for image and text generation.
