Real-time Speech-Text Foundation Model Toolkit (wip)

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

open-source framework for creating and managing simulations populated with AI-powered agents. It provides an intuitive platform for designing complex, interactive environments where agents can act,…

A simple, easy-to-hack GraphRAG implementation

HumanLayer enables AI agents to communicate with humans in tool-based and async workflows. Guarantee human oversight of high-stakes function calls with approval workflows across slack, email and mo…

Kanji vector graphics

Repository for the Lux AI Challenge, season 3 @NeurIPS 24. Hosted on @kaggle

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Whisper with Medusa heads

Various AI scripts. Mostly Stable Diffusion stuff.

Train high-quality text-to-image diffusion models in a data & compute efficient manner

[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

[ECCV 2024] OMG: Occlusion-friendly Personalized Multi-concept Generation In Diffusion Models

A general fine-tuning kit geared toward diffusion models.

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

LLaVA-JP is a Japanese VLM trained by LLaVA method

A repository of Japanese Phoneme-Level BERT

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit

openjtalk形式のユーザー辞書

Code for HyperSeg and HyperSum

Detect file content types with deep learning

Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.