Skip to content

README.md

Latest commit

 

History

History
29 lines (20 loc) · 974 Bytes

README.md

File metadata and controls

29 lines (20 loc) · 974 Bytes
Raw

Moonshine

MLX implementation of Useful Sensors' Moonshine, a lightweight ASR model that processes raw audio through a learned conv frontend rather than mel spectrograms.

Available Models

Model Parameters Description
UsefulSensors/moonshine-tiny 27M Smallest variant
UsefulSensors/moonshine-base 61M Larger, more accurate

Python Usage

from mlx_audio.stt import load

model = load("UsefulSensors/moonshine-tiny")

result = model.generate("audio.wav")
print(result.text)

Architecture

  • 3 layer conv frontend (strides 64, 3, 2) with GroupNorm
  • Transformer encoder with RoPE (6 layers tiny, 8 layers base)
  • Transformer decoder with cross attention and SwiGLU (6 layers tiny, 8 layers base)
  • Byte level BPE tokenizer (32k vocab)
  • 16kHz raw audio input (no mel spectrogram)