Stars
🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉
A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]
Add a virtual speaker and mic to your windows 10/11 device! Works with VR, OBS, Sunshine, and/or any desktop sharing software.
X-VC: Zero-shot Streaming Voice Conversion in Codec Space
Train a neural network that tracks pitch and detects singing in real-time on your laptop, then deploy it to run live in a web browser.
论文Reinforcement Learning of Sequential Price Mechanisms的复现
Setting a reserve price induces this by causing bidders to lose at lower bids which encourages higher bidding and more publisher revenue. However, since most of these take place through automated s…
Bring portraits to life in Real Time!onnx/tensorrt support!实时肖像驱动!
NC-TCN: Noise-Conditional Temporal Convolutional Networks for Robust On-Device Keyword Spotting (ICASSP 2027 / MLSP 2026)
A script to make it easy to swap faces in videos using the faceswap library, and YouTube videos.
Budget Constrained Bidding for Display Advertising using Model-free Reinforcement Learning
the baseline for NeurIPS_Auto_Bidding_AIGB_Track
一个拥有动态生命周期的智能长期记忆插件。
Python toolkit for high-quality time and pitch processing
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
leospark / ClearMic
Forked from smart361/ClearMicClearMic is a professional audio noise cancellation software that provides clear, pure audio experience.
Low-latency AI engine for mobile devices & wearables
DeepVQE reimplementation in PyTorch and GGML — real-time acoustic echo cancellation with soft delay estimation
Implementation of Fish Audio S2 Pro model inference in native ggml.
Lightweight streaming Voice Activity Detection (VAD) tool with ONNX runtime
Voice input for Fcitx5 — local and cloud ASR, LLM rewriting, cross-distro packages
Build, evaluate, and integrate long-term memory for self-evolving agents.