whisperkit-coreml

Executes Whisper automatic speech recognition on Apple devices using Core ML quantized models, converting audio waveforms to text through a compiled, device-optimized neural network that runs locally without cloud connectivity. The quantization reduces model size from ~3GB to ~500MB-1.5GB per variant while maintaining accuracy through post-training quantization techniques, enabling on-device inference on iPhone, iPad, and Mac with hardware acceleration via Neural Engine or GPU.

Automatically detects the spoken language from audio input and transcribes speech across 99 languages using Whisper's multilingual encoder-decoder architecture, without requiring explicit language specification. The model internally learns language-specific acoustic and linguistic patterns during training, enabling zero-shot language identification and cross-lingual transfer for low-resource languages through a shared embedding space.

Generates transcribed text with frame-level timing information, enabling alignment of each word or token to its corresponding audio timestamp (typically 20ms frame granularity). This is achieved through Whisper's decoder attention weights and frame-to-token alignment, allowing downstream applications to synchronize captions, highlight spoken words, or enable seek-to-word functionality in media players.

Provides multiple quantized Whisper model variants (tiny, base, small, medium) with different parameter counts and accuracy profiles, allowing developers to select based on target device capabilities and latency requirements. Each variant is pre-quantized to INT8 or FP16 and compiled to Core ML, with documented accuracy (WER) and inference time benchmarks across device classes (iPhone, iPad, Mac).

Processes multiple audio files sequentially or in batches through the Core ML model, with optional preprocessing steps including audio normalization, silence trimming, and format conversion. The preprocessing pipeline handles common audio issues (clipping, DC offset, variable sample rates) before feeding to the ASR model, improving transcription quality on real-world recordings.

Accepts audio input in streaming chunks (e.g., from microphone or network stream) and buffers them into fixed-size segments, transcribing each segment independently while maintaining context across segments through a sliding window approach. This enables near-real-time transcription feedback without waiting for complete audio, though with latency of 1-2 segments (typically 1-2 seconds).