diff --git a/README.md b/README.md index 798d8b4..2104d76 100644 --- a/README.md +++ b/README.md @@ -36,6 +36,83 @@ The base installation uses the Akiki engine on supported hosts. ONNX and PyTorch provide compatibility fallbacks for VAD. Install `akiki[onnx]` or `akiki[pytorch]` when you need a compatibility engine. +### Windows and macOS + +Native wheels support Windows x64, macOS Intel, and macOS Apple Silicon. +Each wheel includes the Akiki engine for VAD and decision models. +Pip selects the wheel for your Python installation. No engine build is required. +Windows ARM64 wheels are not available. +The macOS wheels target macOS 11.0 or later. + +#### Windows (PowerShell) + +Use 64-bit x86 Python 3.10 or later. +Run these commands in PowerShell: + +```powershell +py -3 -m venv .venv +.\.venv\Scripts\python.exe -m pip install akiki +$env:HF_HUB_OFFLINE = "1" +.\.venv\Scripts\python.exe -m akiki vad ".\recording.wav" --engine akiki +.\.venv\Scripts\python.exe -m akiki vad --help +``` + +Use a mono, 16,000 Hz WAV file for `recording.wav`. +To use an existing local MiniLM/BERT classifier, run: + +```powershell +.\.venv\Scripts\python.exe -m akiki minilm --model "C:\models\my-classifier" "Please save my changes." +``` + +Replace `C:\models\my-classifier` with your local export directory. +The `minilm` command gives direct access to the current decision-model runtime. +Use [`DecisionModel`](#decision-models) to manage saved specialists through Python. + +#### macOS (Terminal) + +Use Python 3.10 or later. +Use a Python installation that matches your Mac's architecture. +Run these commands in Terminal: + +```bash +python3 -m venv .venv +.venv/bin/python -m pip install akiki +export HF_HUB_OFFLINE=1 +.venv/bin/python -m akiki vad "./recording.wav" --engine akiki +.venv/bin/python -m akiki vad --help +``` + +Use a mono, 16,000 Hz WAV file for `recording.wav`. +To use an existing local MiniLM/BERT classifier, run: + +```bash +.venv/bin/python -m akiki minilm --model "./models/my-classifier" "Please save my changes." +``` + +Replace `./models/my-classifier` with your local export directory. +The Python VAD and decision-model APIs below are the same on all supported systems. + +#### VAD compatibility fallback + +If a native wheel is unavailable, use the ONNX compatibility fallback for VAD. +Create a virtual environment as shown in your platform example above. +On Windows, run: + +```powershell +.\.venv\Scripts\python.exe -m pip install "akiki[onnx]" +.\.venv\Scripts\python.exe -m akiki vad ".\recording.wav" --engine onnx +``` + +On macOS, run: + +```bash +.venv/bin/python -m pip install 'akiki[onnx]' +.venv/bin/python -m akiki vad "./recording.wav" --engine onnx +``` + +This fallback uses the bundled VAD model. It does not enable decision-model inference. +PyTorch is the second VAD compatibility fallback. + ## Python usage Use `akiki.vad` for VAD and `akiki.decision` for decision models. @@ -139,6 +216,7 @@ ONNX and PyTorch are VAD compatibility fallbacks. Linux x86_64 wheels include the Akiki engine for systems with glibc 2.34 or later. Pip and uv select a compatible wheel automatically. No engine build is required. +For Windows and macOS, see the [platform installation examples](#windows-and-macos). Version **0.1.2** includes **Linux ARM64 VAD support**, including Raspberry Pi 5 with a 64-bit OS and glibc 2.28 or later. This wheel includes the Akiki VAD library @@ -686,8 +764,10 @@ between texts. Keep the instance open until all worker calls have finished. longer than `model.max_tokens`. `encode_chunks()` requires complete token sequences and positive finite weights. It adds no special tokens. -MiniLM requires the Akiki engine included in Linux x86_64 and ARM64 wheels; -**ARM64 MiniLM support is experimental**. It has no ONNX or PyTorch alternative. +MiniLM requires the Akiki engine included in native wheels. +These wheels support Linux x86_64 and ARM64, Windows x64, and macOS Intel and Apple Silicon. +See the [Windows and macOS examples](#windows-and-macos) for current wheel availability. +**Linux ARM64 MiniLM support is experimental**. It has no ONNX or PyTorch alternative. It uses up to four CPU threads by default; set `threads` to change this. Projections use `akiki.decision.ModelPrecision.INT8` by default. To use the original weights: