Stars
Independent CarPlay receiver for compatible Android head units. Wired and wireless public preview.
Official implementation of “Learning Where to Split: Dynamic Band Splitting for Audio Source Separation”
IIR Modeling of Spherical Microphone Array Signals
Reverse engineer anything with agents, from app behavior down to native binaries.
Estimation of Room Impulse Responses from Handclaps
Samsone: A Family of Open Small Audio Language Models for On-Device Inference
Official implementation of Continual Residual Memory (CRM) for Speech Enhancement.
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Chatterbox-Flash: Extending Chatterbox with Block Diffusion for Fast Speech Generation
Open-source realtime voice agent server in Go with WebRTC (WHIP), barge-in, streaming STT/LLM/TTS pipelines, plugin system, multi-language SDKs, SIP telephony, ESP32 support & fully local mode.
Training code and dataset cleasing with Sidon
Private source preview: native Jianying drafts, isolated editing/export, and standalone Agent Skill.
Make any agent harness multimodal-native.
Confucius4-R2T2: A Low Latency and High Accuracy Real-Time Speech Recognition Model
World's fastest and most advanced password recovery utility
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
A Streaming-Native Serving Engine for TTS/STS Models
A high-performance, universal serving framework for any-to-any models.
Ultrafast Qwen3-TTS: sub-50 ms time-to-first-audio at 10 requests per second.
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (N…
A Robust Low-Latency Streaming Zero-Shot Voice Conversion
Official repository of the paper "On-Policy Self-Distillation for Multi-Dialect ASR: Mastering Dialects, Retaining Mandarin".