The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…

Spark-TTS Inference Code

SOTA Open Source TTS

网易云无损解析

Efficient Triton Kernels for LLM Training

SGLang is a fast serving framework for large language models and vision language models.

Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth

Generative models for conditional audio generation

An open agentic system built on smolagents, integrating multimodal state-of-the-art music AI models for understanding, generation, and interaction.

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

Context engineering is the new vibe coding - it's the way to actually make AI coding assistants work. Claude Code is the best for this so that's what this repo is centered around, but you can apply…

An open-source AI agent that lives in your terminal.

轻量、灵活、易上手的Python剪映草稿生成及导出工具，构建全自动化视频剪辑/混剪流水线。本项目的CapCut版本正于 https://github.com/GuanYixuan/pyCapCut 内开发

Open-source unified multimodal model

PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

The official code repository for SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement

No fortress, purely open ground. OpenManus is Coming.

FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build AI workflow platforms faster and simpler.

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics rec…

ACE-Step: A Step Towards Music Generation Foundation Model

Dataset and code of GTSinger(NeurIPS 2024 Spotlight): A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

PyTorch-implementations of Flow Models for toy data

Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

A Model Context Protocol server for searching and analyzing arXiv papers

Encode and decode audio samples to/from compressed latent representations!

Multilingual Voice Understanding Model