You can deploy this model and start earning money today!

mira-thing/
mira-voice

Name: mira-voice
Availability: InStock

sherpa-onnx

tflite

onnx

automatic-speech-recognition

Views

No views yet

mira-voice - prebuilt on-device voice runtime (aarch64)

Prebuilt model + runtime bundle for Mira, the 100%-on-device smart-voice stack for the discontinued Spotify Car Thing. This repo holds the heavy, upstream artifacts. The code, build scripts, and the one custom model (the "hey mira" wake word) live on GitHub at mira-thing/mira-voice.

This is a deployment bundle, not a transformers loadable model. Fetch it via the repo's fetch-artifacts.sh, or huggingface-cli download mira-thing/mira-voice.

Path	What	Upstream	License
`zipformer/...gigaspeech.../`	sherpa-onnx Zipformer int8 ASR (encoder/decoder/joiner + tokens/bpe)	k2-fsa	Apache-2.0
`lib/`	aarch64 runtime: ONNX Runtime, TFLite, sherpa-onnx, glibc family, audio libs	mixed	see `THIRD_PARTY_LICENSES`
`models/melspectrogram.tflite`, `embedding_model.tflite`	openWakeWord shared base models	openWakeWord	Apache-2.0
`espeak-ng-data/`	espeak-ng g2p data, trimmed to en-us	espeak-ng	GPL-3.0
`bin/`	aarch64 helpers: `oww_wake`, `sherpa_asr_server`, `espeak-ng`	this project + espeak-ng	see repo

Not in this bundle: the hey_mira.tflite wake model, version-controlled in the GitHub repo.

Use

git clone https://github.com/mira-thing/mira-voice && cd mira-voice
bash fetch-artifacts.sh 

The sherpa Zipformer is the unmodified k2-fsa GigaSpeech release; the runtime .so are upstream libraries cross-built for aarch64. Full attribution in THIRD_PARTY_LICENSES.

mira-thing/mira-voice

mira-voice - prebuilt on-device voice runtime (aarch64)

Contents

Use

mira-thing/
mira-voice