Torq Models
Collection
AI Models compiled with the Torq Compiler for execution on Torq enabled SoCs • 6 items • Updated
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.
Moonshine Tiny has been optimized for the Synaptics Astra™ SL2610-Series processors with Torq NPU.
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)
Deployment
The compiled model files are available for download on Huggingface at Synaptics/Moonshine.
Usage tutorial to be available in the future at Synaptics AI Developer Zone.
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.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Synaptics/moonshine-tiny-bf16-torq
Base model
UsefulSensors/moonshine