Speech Recognition
TheStageAI/TheWhisper๐ฅ active
Optimized Whisper models for streaming and on-device use
PythonMITupdated Sep 23, 2026
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
$ git clone https://github.com/QuentinFuxa/WhisperLiveKit.gitOptimized Whisper models for streaming and on-device use
very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust
ARIA - AI Realtime Intelligent Audio | Universal real-time AI subtitles for Windows
Ultra fast and portable Parakeet implementation for on-device inference in C++ using Axiom with MPS+Unified Memory
End-to-End Speech Processing Toolkit
Data from GitHub ยท snapshot Sep 24, 2026