sherpa-onnx
ποΈ Production-grade On-Device Speech-to-Text & 128d X-Vector Speaker Diarization for Android Termux. whisper.cpp, Vosk, Sherpa-ONNX, and 0 PyTorch Dependency.
One interface to run and compare any speech-to-text β local & cloud / δΈε₯ζ₯ε£,θ·ιη«―δΊζζθ―ι³θ―ε«
Fast, private, and simple transcription for any media file using local models, even without a GPU
Local Whisper transcription + speaker diarization for Apple Silicon β who said what, fully offline and on-device
Real-time speech-to-text clipboard tool with Silero VAD and local ASR support