分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.

🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

😘 让你“爱”上 GitHub，解决访问时图裂、加载慢的问题。（无需安装）

Turn (almost) any Python command line program into a full GUI application with one line

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

A hyperparameter optimization framework

An open access book on scientific visualization using python and matplotlib

Accessible large language models via k-bit quantization for PyTorch.

🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目，支持ChatGPT多轮对话能力，还可能是首个支持脑机交互的开源智能音箱项目。

Play ChatGPT and other LLM with Xiaomi AI Speaker

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

Automatic integrate all Xiaomi devices to HomeAssistant via miot-spec, support Wi-Fi, BLE, ZigBee devices. 小米米家智能家居设备接入Hass集成

AudioLDM: Generate speech, sound effects, music and beyond, with text.

📊 Save matplotlib figures as TikZ/PGFplots for smooth integration into LaTeX.

XiaoMi Cloud Service for mi.com

A GPU accelerated and torch based audio DSP library

A Python Module for Simulating Active Noise Control Experiments

This project implements adaptive filter algorithms for **Acoustic Echo Cancellation (AEC)** and general audio processing,

Real-time partitioned convolution algorithms for Finite Impulse Response (FIR) filters in Python.

Audio speech emotion recognition using Temporal Convolutional Networks (TCNs)

Study of HRTF interpolation via spherical harmonic representation

minimal example for iirnet testing

Computer vision to interact with virtual reality scenarios using hand gestures

Interactive plots to study audio clusters: visualize and listen to clustered data

A Lightweight Python API for the AES69-2015 Spatially Oriented Format for Acoustics (SOFA) File Format

Audio emotion recognition with convnets