Stars
📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors
Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
T-one is a high-performance streaming ASR pipeline for Russian, specialized for the telephony domain.
Rich is a Python library for rich text and beautiful formatting in the terminal.
DSPy: The framework for programming—not prompting—language models
SGLang is a fast serving framework for large language models and vision language models.
📹 A more flexible framework that can generate videos at any resolution and creates videos from images.
The official code for "MagCache: Fast Video Generation with Magnitude-Aware Cache"
A lightweight, powerful framework for multi-agent workflows
Most Useful WoW Addons for Patch 3.3.5a WotLK
A unified inference and post-training framework for accelerated video generation.
Official implementation of ATI: Any Trajectory Instruction for Controllable Video Generation. https://arxiv.org/pdf/2505.22944
Deep Neural Pitch Extractor for Voice Conversion and TTS Training
Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)
Inference and training library for high-quality TTS models.
Build Real-Time Knowledge Graphs for AI Agents
Code and Resources for "LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study", introducing methods to leverage LLMs for G2P tasks without additional training, featuring Sentence-Ben…
[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
A versatile, self-hosted manga reader and manager with extensible agent-based metadata retrieval
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
Lets make video diffusion practical!
[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing
neosr is an open-source framework for training super-resolution models.