Spaces:
Running
Running
|
Download README.md from Snapdragon-AI-Stack/README: direct link, hf CLI and curl.
- Browser
- Download file 1.85 kB
-
https://huggingface.co/spaces/Snapdragon-AI-Stack/README/resolve/main/README.md
- Command line
-
hf download hf://spaces/Snapdragon-AI-Stack/README/README.md
-
curl -L -o README.md https://huggingface.co/spaces/Snapdragon-AI-Stack/README/resolve/main/README.md
1.85 kB
| title: README | |
| emoji: π | |
| colorFrom: green | |
| colorTo: yellow | |
| sdk: static | |
| pinned: false | |
| license: mit | |
| short_description: High-performance, NPU-accelerated AI and speaker diarization | |
| # Snapdragon-AI-Stack π | |
| **Optimized SOTA AI for the Windows ARM64 Ecosystem.** | |
| 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. | |
| --- | |
| ## ποΈ Our Focus Areas | |
| - **ποΈ SnapNote:** High-performance transcription and diarization pipelines (Whisper Turbo + Pyannote 3.1) running natively on the Hexagon NPU. | |
| - **π¦ NPU-Ready Model Zoo:** Quantized ONNX weights specifically calibrated for the `QNNExecutionProvider`. | |
| - **π‘ Wheel Factory:** Pre-compiled `win_arm64` wheels for PyTorch, Torchaudio, and hf-transfer to ensure seamless installation on Windows 11 ARM. | |
| --- | |
| ## π The NPU Advantage | |
| By offloading tensor operations from the CPU to the NPU on Snapdragon laptops, we achieve: | |
| * **Efficiency:** Up to 80% reduction in CPU power draw. | |
| * **Speed:** Faster-than-real-time diarization and inference. | |
| * **Mobility:** Professional-grade AI workflows that don't sacrifice battery life. | |
| --- | |
| ## π οΈ Quick Links | |
| * **Main Organization:** [Snapdragon-AI-Stack on GitHub](https://github.com/Snapdragon-AI-Stack) | |
| * **Binary Builds:** [PyTorch QNN Wheels](https://github.com/Snapdragon-AI-Stack/pytorch-qnn) | |
| * **Fast Downloads:** [hf-transfer-qnn](https://github.com/Snapdragon-AI-Stack/hf-transfer-qnn) | |
| --- | |
| ## π€ Community & Collaboration | |
| We are actively seeking contributors with expertise in the **Qualcomm AI Stack**, **ONNX Runtime quantization**, and **Windows ARM64 development**. | |
| *"Making the Hexagon NPU the heart of your AI workflow."* |