FunASR SenseVoice-Small speech-to-text inference snap (Myna)
Local, offline speech-to-text service exposing the Myna session API on a
Unix domain socket. Wraps SenseVoice-Small (FunASR, Alibaba DAMO Academy)
served via ONNX Runtime, covering Chinese, English, Cantonese, Japanese, and
Korean.
The service receives PCM audio pushed by clients; it has no access to the
microphone or any audio hardware.