# Hush v0.1.0

Stage: **research baseline**. Not published to npm or Maven.

Synthetic harmonic, noise and silence signals. Voice-like is not validated speech detection; no real speech benchmark.

## Artifact

- Raw bytes: 341
- SHA-256: `0b797537dcb4e3c016f6ebae2bc64898ccd727bb042b999c078b45ef702913c3`
- Training examples: 240
- Internal held-out smoke test: 60/60
- Classes: Voice-like, Other

The internal test is not an independent real-world benchmark. Scores are uncalibrated. Artifact size excludes the runtime and memory overhead.

## Node / browser

From the repository root: `bun install && bun run sdk:build`.

```ts
import { createModel } from '@embermote/hush';
const model = createModel();
```

Text models accept a string. Audio models accept `audioFeatures(pcm, 8000)`; Glyph accepts `shapeFeatures(points)`, both exported by `@embermote/core`.

## Kotlin

```kotlin
import dev.embermote.hush.Hush
val model = Hush.load()
```

JDK 17+, root Gradle build. Model resources are bundled in each model module. Use `Features.audio` or `Features.shape` for numeric inputs. Android device testing is pending.

## Rebuild

`bun run train` uses the original recipe in `training/train.py`. No external datasets or third-party weights are downloaded.