sensevoice-rs and sensevoice-cli

These are ecosystem siblings where one provides a Rust library binding (darkautism/sensevoice-rs) and the other is a CLI wrapper tool (miuda-ai/sensevoice-cli) built on top of the same SenseVoice-small model, allowing users to choose between programmatic or command-line interfaces for the same underlying functionality.

sensevoice-rs
39
Emerging
sensevoice-cli
27
Experimental
Maintenance 13/25
Adoption 11/25
Maturity 1/25
Community 14/25
Maintenance 6/25
Adoption 7/25
Maturity 1/25
Community 13/25
Stars: 27
Forks: 5
Downloads: 66
Commits (30d): 0
Language: Rust
License: —
Stars: 26
Forks: 4
Downloads: —
Commits (30d): 0
Language: Rust
License: —
No License No Package No Dependents
No License No Package No Dependents

About sensevoice-rs

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.

About sensevoice-cli

miuda-ai/sensevoice-cli

Tool for speech recognition using sensevoice-small

Scores updated daily from GitHub, PyPI, and npm data. How scores work