Spaces:
Running
Running
Updated Project Card.
Browse files
README.md
CHANGED
|
@@ -9,4 +9,41 @@ license: mit
|
|
| 9 |
short_description: High-performance, NPU-accelerated AI and speaker diarization
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
short_description: High-performance, NPU-accelerated AI and speaker diarization
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Snapdragon-AI-Stack π
|
| 13 |
+
|
| 14 |
+
**Optimized SOTA AI for the Windows ARM64 Ecosystem.**
|
| 15 |
+
|
| 16 |
+
Welcome to the official Hugging Face home of the **Snapdragon-AI-Stack**. Our mission is to transform the **Qualcomm Snapdragon X Elite/Plus** into a powerhouse for Artificial Intelligence by providing NPU-accelerated models and native binaries.
|
| 17 |
+
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
## ποΈ Our Focus Areas
|
| 21 |
+
|
| 22 |
+
- **ποΈ SnapNote:** High-performance transcription and diarization pipelines (Whisper Turbo + Pyannote 3.1) running natively on the Hexagon NPU.
|
| 23 |
+
- **π¦ NPU-Ready Model Zoo:** Quantized ONNX weights specifically calibrated for the `QNNExecutionProvider`.
|
| 24 |
+
- **π‘ Wheel Factory:** Pre-compiled `win_arm64` wheels for PyTorch, Torchaudio, and hf-transfer to ensure seamless installation on Windows 11 ARM.
|
| 25 |
+
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
## π The NPU Advantage
|
| 29 |
+
|
| 30 |
+
By offloading tensor operations from the CPU to the NPU on Snapdragon laptops, we achieve:
|
| 31 |
+
* **Efficiency:** Up to 80% reduction in CPU power draw.
|
| 32 |
+
* **Speed:** Faster-than-real-time diarization and inference.
|
| 33 |
+
* **Mobility:** Professional-grade AI workflows that don't sacrifice battery life.
|
| 34 |
+
|
| 35 |
+
---
|
| 36 |
+
|
| 37 |
+
## π οΈ Quick Links
|
| 38 |
+
|
| 39 |
+
* **Main Organization:** [Snapdragon-AI-Stack on GitHub](https://github.com/Snapdragon-AI-Stack)
|
| 40 |
+
* **Binary Builds:** [PyTorch QNN Wheels](https://github.com/Snapdragon-AI-Stack/pytorch-qnn)
|
| 41 |
+
* **Fast Downloads:** [hf-transfer-qnn](https://github.com/Snapdragon-AI-Stack/hf-transfer-qnn)
|
| 42 |
+
|
| 43 |
+
---
|
| 44 |
+
|
| 45 |
+
## π€ Community & Collaboration
|
| 46 |
+
|
| 47 |
+
We are actively seeking contributors with expertise in the **Qualcomm AI Stack**, **ONNX Runtime quantization**, and **Windows ARM64 development**.
|
| 48 |
+
|
| 49 |
+
*"Making the Hexagon NPU the heart of your AI workflow."*
|