Skip to main content

Moonshine Tiny BF16

A high-efficiency automatic speech recognition model using variable-length architecture for real-time speech recognition, optimized for 16kHz mono audio.

Supported processors

  • SL2619

Performance

Torq Compiler/Runtime v2.3.0

193.602ms
Inference Time
69.7tok/s
Tokens per Second
0.12
Real-Time Factor
55.9MB
DRAM Footprint

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-tiny-bf16-torq.

Usage Tutorial​

A usage example is provided at Torq Examples / moonshine. Check out the README for instructions.

License​

Both the source model and the compiled model for on-device deployment are licensed under MIT License.

Learn More​

Related models