darkautism/sensevoice-rs
A Rust-based, SenseVoiceSmall
Implements multi-backend ASR with Candle for CPU/GPU inference and optional RKNN runtime for Rockchip NPU acceleration, eliminating external ONNX dependencies. Combines voice activity detection (FSMN-VAD) with language/emotion/event classification from PyTorch model files, supporting both file and streaming audio inputs. Integrates with Hugging Face Hub for automatic model downloads and targets embedded systems alongside standard platforms via conditional feature gates.
Stars
27
Forks
5
Language
Rust
License
—
Category
Last pushed
Mar 09, 2026
Monthly downloads
66
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/darkautism/sensevoice-rs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
TrevorS/voxtral-mini-realtime-rs
Streaming speech recognition running natively and in the browser. A pure Rust implementation of...
izwi-ai/izwi
On-device AI engine for transcription, TTS, and voice workflows.
mrtozner/vox
Local voice AI framework for Rust. Whisper + LLM + TTS with no cloud dependencies.
thewh1teagle/vad-rs
Speech detection using silero vad in Rust
0xPD33/sonori
Sonori is a fully local STT app for Linux (Wayland).