yooz-labs: initial org profile
Browse files
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Yooz Labs
|
| 2 |
+
|
| 3 |
+
**Sovereign Intelligence. Built for the skeptical.**
|
| 4 |
+
|
| 5 |
+
Privacy-first AI that runs entirely on your devices. No cloud, no tracking, no compromises.
|
| 6 |
+
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
## What we're building
|
| 10 |
+
|
| 11 |
+
We're the privacy infrastructure for the AI decade. Every Yooz product is designed for the 70% of consumers who don't trust cloud AI but lack consumer-grade alternatives.
|
| 12 |
+
|
| 13 |
+
- **Yooz Engine** — unified local AI service for macOS (STT, LLM, grammar, VAD, TTS).
|
| 14 |
+
- **Yooz Whisper** — voice keyboard for macOS.
|
| 15 |
+
- **Yooz Notes** — note-taking with private AI memory.
|
| 16 |
+
- **Yooz Vault** — privacy hardware (home server).
|
| 17 |
+
- **Universal AI Platform Layer** — one API across Apple Core ML, Android ML Kit, Windows DirectML.
|
| 18 |
+
|
| 19 |
+
## What lives on this Hugging Face org
|
| 20 |
+
|
| 21 |
+
The **model weights** — Apache 2.0, fully open source. The Yooz product code is source-available on GitHub under PolyForm Shield, but the weights stay open so the research community can build on them, audit them, and remix them.
|
| 22 |
+
|
| 23 |
+
### Model categories
|
| 24 |
+
|
| 25 |
+
| Category | What it is |
|
| 26 |
+
|---|---|
|
| 27 |
+
| **ASR** | Speech-to-text checkpoints (Qwen3-ASR Swift port, Parakeet derivatives) |
|
| 28 |
+
| **LLMs (Touchup)** | Fine-tuned small LLMs that fix/clean speech-to-text transcripts |
|
| 29 |
+
| **Distillations** | Small students distilled from larger teachers for on-device inference |
|
| 30 |
+
| **Adapters** | LoRA / DoRA adapters published alongside their fused checkpoints |
|
| 31 |
+
|
| 32 |
+
All checkpoints document their **lineage** (base model + Hugging Face link), **eval numbers** (real benchmarks, not vibes), and **Swift / Python usage snippets**.
|
| 33 |
+
|
| 34 |
+
## Why open weights?
|
| 35 |
+
|
| 36 |
+
The competitive moat in privacy-first AI lives in the **product**, not the weights:
|
| 37 |
+
|
| 38 |
+
- Multi-device orchestration (phone → PC → Vault) over WireGuard mesh.
|
| 39 |
+
- Universal platform abstraction across Apple, Android, Windows AI APIs.
|
| 40 |
+
- Private AI memory: encrypted, local, with permissioned cross-app context.
|
| 41 |
+
- Beautiful, consumer-grade UX.
|
| 42 |
+
|
| 43 |
+
The weights themselves should be open so the research community can audit privacy claims, reproduce evals, and build on top. Releases follow the standard "ship the artifact + the recipe to reproduce it."
|
| 44 |
+
|
| 45 |
+
## Provenance
|
| 46 |
+
|
| 47 |
+
We never train on user data without opt-in. All training corpora and synthetic data sources are documented in the model card for each checkpoint. Where we fine-tune from a base model (Qwen, Gemma, etc.), the lineage is preserved and the upstream license is respected.
|
| 48 |
+
|
| 49 |
+
## Source-available, not closed
|
| 50 |
+
|
| 51 |
+
The product code lives at [github.com/yooz-labs](https://github.com/yooz-labs) under PolyForm Shield. You can read it, fork it, and build on it for non-competing use cases. We chose this path because we want to stay community-aligned without enabling AWS-style "managed Yooz" competing services.
|
| 52 |
+
|
| 53 |
+
## Get in touch
|
| 54 |
+
|
| 55 |
+
- **Engineering & research**: shirazi@ieee.org
|
| 56 |
+
- **Bugs and feature requests**: file on the relevant GitHub repo under [yooz-labs](https://github.com/yooz-labs)
|
| 57 |
+
- **Mailing list / news**: coming soon
|
| 58 |
+
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
*We're building the privacy infrastructure for the AI decade. Every decision prioritizes user sovereignty, data privacy, and beautiful simplicity.*
|