# moonshine

| | |
|---|---|
| **Model type** | `moonshine` |
| **Class** | `MoonshineForConditionalGeneration` |
| **Task** | `speech-to-text` |
| **Source** | `models/moonshine.py` |

## Description

Moonshine RoPE encoder-decoder model for raw-waveform speech recognition.

## Usage

```bash
mobius build --model <MODEL_ID> output_dir/
```

```python
from mobius import build

model = build("<MODEL_ID>")
```