Moonshine Tiny
Model Overview
Moonshine is a high-efficiency automatic speech recognition (ASR) model designed specifically for real-time speech recognition. Unlike Whisper, which processes audio in fixed 30-second chunks, Moonshine uses a variable-length architecture that only computes the actual duration of the speech received.
Useful Sensors developed Moonshine and released the English model as open-source. There are 2 models of different sizes and capabilities - base and tiny. The tiny version utilizes 27M parameters.
Model Features
- Model Type: Automatic Speech Recognition
- Input: Raw waveform (1D array of floats) 16kHz mono audio up to 30 seconds
- Output: Sequence of token IDs (integers)
- Quantization: None
Recommended Platforms
- Synaptics Astra™ SL2600-Series with Torq
- Synaptics Astra™ SL1600-Series with Synap
Metrics
| Platform | Model / Stage | Environment | Inference Time | Infer / s |
|---|---|---|---|---|
| SL2610 | Moonshine Tiny Decoder | Torq v2.0.0 | 15.6 | 64.1 |
| SL2610 | Moonshine Tiny Encoder (5 sec audio) | Torq v2.0.0 | 156.1 | 6.4 |
Deployment
Compiled Models
Torq compiled model files are provided in this repository. To recompile the models, see the Torq Documentation.
Source Models
The source model files are available at Synaptics/Moonshine.
Usage Tutorials / Example Apps
Synaptics AI Developer Zone Tutorials
Example App GitHub Repositories
- Torq Examples: Basic model usage examples for Torq
- SL2610 Examples: Interactive examples for SL2610-Series
License
Both the source model and the compiled model for on-device deployment are licensed under MIT License.
Learn More
- Synaptics AI Developer Zone: Get started with documentation, tutorials and resources for your Edge AI journey.
- Astra Support Portal: Connect with our engineering team and community.