Speech Recognition
wwbin2017/bailing
百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,集成DeepSeek R1等优秀大模型,接入openClaw,真正的个人语音助手,时延低至800ms,Mac等低配置也可运行,支持打断
PythonMITupdated Apr 6, 2026
快速提取音视频内容,整理成一份结构化的markdown笔记
$ git clone https://github.com/harry0703/AudioNotes.git百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,集成DeepSeek R1等优秀大模型,接入openClaw,真正的个人语音助手,时延低至800ms,Mac等低配置也可运行,支持打断
▲ +4 ★ this week
A lightweight Python package for Automatic Speech Recognition using ONNX models
▲ +9 ★ this week
ARIA - AI Realtime Intelligent Audio | Universal real-time AI subtitles for Windows
Open-source phoneme-level English pronunciation assessment (Wav2Vec2 + DTW). Self-hosted alternative to Azure Pronunciation Assessment.
Data from GitHub · snapshot Nov 13, 2026