Repository files navigation

OtosakuKWS is a lightweight, privacy-focused keyword spotting engine for iOS, designed to detect speech commands in real time — entirely on device.

It uses a CRNN CoreML model combined with log-Mel spectrograms for fast, accurate, and low-latency voice command recognition.

Watch the model running live on iPhone 13:

This project depends on theOtosakuFeatureExtractor-iOS Swift package, which extracts log-Mel spectrograms in real time using Accelerate.

It also includes a ready-to-use filterbank archive (filterbank.npy,hann_window.npy).

The CRNN model was trained on the keywords:“go”, “no”, “stop”, “yes”

⬇️ Download model archive

Includes:

• CRNNKeywordSpotter.mlmodelc
• classes.txt

The model was trained on a balanced subset of [Google Speech Commands v2], using strong augmentations and class balancing.

letkws=tryOtosakuKWS(    modelRootURL: modelURL,    featureExtractorRootURL: featurizerURL,    configuration:.init())kws.onKeywordDetected={ keyword, confidenceinprint("Detected:\(keyword) [\(confidence)]")}letaudioInput=AudioStreamer()// The `onBuffer` callback receives a chunk of audio sampled at 16kHz, mono (1 channel).// `AudioStreamer` here is a dummy real-time microphone streamer that simulates live input.audioInput.onBuffer={ bufferinTask{await kws.handleAudioBuffer(buffer)}}

If you need a custom KWS model for your use case — different keywords, languages, or domain-specific speech — feel free to reach out:

📧otosaku.dsp@gmail.com

CoreML, keyword spotting, speech commands, offline voice recognition, privacy-first AI, log-Mel spectrogram, iOS speech processing, CRNN, on-device inference, streaming audio, Swift AI