README.md

---
license: mit
base_model: UsefulSensors/moonshine-tiny
pipeline_tag: automatic-speech-recognition
library_name: openasr
tags:
  - automatic-speech-recognition
  - speech-to-text
  - openasr
  - oasr
  - moonshine
---

<div align="center">

# Moonshine Tiny · OpenASR

**Tiny 27M-parameter English ASR built for real-time, on-device transcription**

[![License](https://img.shields.io/badge/license-MIT-2563eb.svg)](https://huggingface.co/UsefulSensors/moonshine-tiny)
[![Format](https://img.shields.io/badge/format-.oasr-7c3aed.svg)](https://github.com/QuintinShaw/openasr)
[![Runtime](https://img.shields.io/badge/runtime-OpenASR-111827.svg)](https://openasr.org)
[![Base model](https://img.shields.io/badge/base-moonshine--tiny-f59e0b.svg)](https://huggingface.co/UsefulSensors/moonshine-tiny)

Native speech-to-text in the **[OpenASR](https://github.com/QuintinShaw/openasr)** runtime —
engineered for peak performance on CPU & GPU, **no Python at inference time**.

</div>

---

## ✨ Highlights

- 🪶 **Just 27M parameters** — the smallest Moonshine, sized for memory- and compute-constrained edge hardware
- ⚡ **Real-time on-device** — engineered by Useful Sensors for live transcription and voice commands on low-cost devices
- 🎯 **Accurate for its size** — beats similarly-sized ASR systems on standard English benchmarks (per the Moonshine paper)
- 🗣️ **English speech-to-text** — sequence-to-sequence ASR trained on 200K hours of audio
- 🦀 **Native in OpenASR** — `.oasr` packs run with no Python at inference, engineered for peak performance on CPU & GPU

## 🚀 Quickstart

```bash
# 1. Install the OpenASR CLI  ·  https://openasr.org
# 2. Pull a build (pick a quant — see the table below)
openasr pull moonshine-tiny:q8

# 3. Transcribe
openasr transcribe audio.wav --model moonshine-tiny
```

All builds for this model:

```bash
openasr pull moonshine-tiny:fp16
openasr pull moonshine-tiny:q8
```

## 📦 Available builds

| Quant | File (`.oasr`) | Size | RAM peak | RTF · M1 CPU | RTF · M1 GPU | JFK ΔWER vs fp16 |
|:------|:---------------|-----:|---------:|-------------:|-------------:|-----------------:|
| fp16 | `moonshine-tiny-fp16.oasr` | 109 MB | 323 MB | 0.04× | 0.03× | 0.0% |
| q8_0 | `moonshine-tiny-q8_0.oasr` | 34 MB | 306 MB | 0.03× | 0.03× | 0.0% |

<sub>RTF = real-time factor on the fixed 11s JFK clip (**lower is faster**); RAM peak measured per pack
in an isolated subprocess. JFK ΔWER compares each quantized build's JFK transcript to this model's
fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy.
**q8_0** is the recommended default — near-reference quality at a fraction of the
footprint.</sub>

## 🧠 About Moonshine Tiny

Moonshine Tiny is the smallest model in Useful Sensors' **Moonshine** family — a 27M-parameter,
sequence-to-sequence English speech-recognition model designed for **real-time, on-device
transcription** on hardware that is severely constrained in memory and compute. Trained on 200,000
hours of audio, it transcribes English speech to text and, despite its size, reports greater accuracy
than existing ASR systems of comparable scale on standard benchmarks. It targets developers building
live transcription and voice-command experiences on low-cost devices. Like other autoregressive ASR
models it can occasionally hallucinate or repeat on very short or clipped segments, so robust
in-domain evaluation is recommended before deployment. This OpenASR repo repackages the original
weights as `.oasr` packs that run natively in the OpenASR runtime — no Python at inference time. The
**q8_0** build is the recommended default (near-reference accuracy at roughly a third of the
footprint); **fp16** is for verification or maximum fidelity.

## ⚙️ How these packs were made

Converted from [UsefulSensors/moonshine-tiny](https://huggingface.co/UsefulSensors/moonshine-tiny) with the OpenASR importer:

```bash
openasr model-pack import-moonshine-local <src> <out>.oasr \
  --package-id moonshine-tiny --quantization {fp16,q8-0,q4-k}
```

The `.oasr` container is GGUF-backed; packs use zero-copy mmap weight binding and graph
buffer reuse to keep peak memory low.

## ⚖️ License

These packs **inherit the upstream model's license: MIT**
([source](https://huggingface.co/UsefulSensors/moonshine-tiny)). OpenASR packaging retains the upstream copyright and
NOTICE; the only modifications are format conversion and quantization.

## 🙏 Acknowledgements

This pack is a redistribution of **Moonshine Tiny**, created and open-sourced by **Useful Sensors**
([UsefulSensors/moonshine-tiny](https://huggingface.co/UsefulSensors/moonshine-tiny)). All credit for
the original architecture, training, and weights belongs to them; the license is inherited from and
identical to the upstream model (MIT). Thank you to the Moonshine authors — Nat Jeffries, Evan King,
Manjunath Kudlur, Guy Nicholson, James Wang, and Pete Warden — for releasing their work openly.

## 🔗 Links

- 🦀 **OpenASR** — <https://github.com/QuintinShaw/openasr>
- 🌐 **Website** — <https://openasr.org>
- 🤗 **Upstream model** — [UsefulSensors/moonshine-tiny](https://huggingface.co/UsefulSensors/moonshine-tiny)