KWS-Zipformer-3M-CoreML-INT8

KWS Zipformer 3M — CoreML INT8

Streaming, zero-shot, open-vocabulary keyword spotting for iOS / macOS / visionOS. Exported from icefall's KWS-finetuned Zipformer transducer (gigaspeech, 3.49M parameters) to CoreML with INT8 palettized weights, FP16 compute, and an iOS 17+ minimum deployment target.

Given an arbitrary list of English keywords at runtime (no retraining required), the model emits a match when it hears one. Runs ~26× real-time on Apple Silicon CPU + Neural Engine.

Model

Files

Performance

Measured on Apple Silicon (CPU + Neural Engine), tuned defaults ac_threshold=0.15 context_score=0.5 num_trailing_blanks=1.

Latency (per call)

Accuracy (LibriSpeech test-clean, 12 keywords, 158 positive + 60 negative utterances)

False positive rate: 0.27 / utterance on 60 random negative utterances. CoreML INT8 output agrees with the PyTorch FP32 reference on 99% of utterances (FP16 palettization drift is not systematic).

Note on "MISTER": SentencePiece tokenizes it as [▁MI, S, TER] (3 tokens). Stateless transducers rarely lock onto 3-token sequences in beam search. For production wake words, prefer single-token keywords.

Memory

Loaded all three .mlmodelc models: peak RSS delta ≈ 63 MB on macOS. After 218-utterance streaming workload: +127 MB total.

Usage

Python (coremltools)

import json
from pathlib import Path

import coremltools as ct
import numpy as np

model_dir = Path("./KWS-Zipformer-3M-CoreML-INT8")
config = json.loads((model_dir / "config.json").read_text())

encoder = ct.models.CompiledMLModel(str(model_dir / "encoder.mlmodelc"))
decoder = ct.models.CompiledMLModel(str(model_dir / "decoder.mlmodelc"))
joiner = ct.models.CompiledMLModel(str(model_dir / "joiner.mlmodelc"))

# Build zero state from config
state = {}
for name, shape in zip(config["encoder"]["layerStateNames"],
                       config["encoder"]["layerStateShapes"]):
    state[name] = np.zeros(shape, dtype=np.float32)
state["cached_embed_left_pad"] = np.zeros(
    config["encoder"]["cachedEmbedLeftPadShape"], dtype=np.float32)
state["processed_lens"] = np.zeros((1,), dtype=np.int32)

# Feed 45 mel frames (80-dim fbank) per chunk
x = np.zeros((1, 45, 80), dtype=np.float32)  # replace with real fbank
out = encoder.predict({"x": x, **state})
encoder_out = out["encoder_out"]                  # (1, 8, 320) in joiner space
# Stream: feed encoder_out[0, t] into decoder/joiner + beam search

Swift (speech-swift)

import SpeechSwift

let model = try await KWSZipformerModel.fromPretrained(
    "aufklarer/KWS-Zipformer-3M-CoreML-INT8"
)
let stream = model.streamingSession(keywords: ["HEY SONIQO", "STOP", "LIGHTS ON"])
try stream.feed(audio: pcm16k)
for match in stream.emissions {
    print("matched: \(match.phrase) at \(match.timestamp)")
}

Reference Python decoder

The upstream Aho-Corasick ContextGraph + boost-cancellation beam search algorithm is available as a dependency-free pure-Python reference for porting to other runtimes.

Source

Exported from icefall-kws-zipformer-gigaspeech-20240219 (Apache-2.0), specifically the exp-finetune/pretrained.pt KWS-finetuned checkpoint, published in pkufool/keyword-spotting-models v0.11.

The reference ONNX export is csukuangfj/sherpa-onnx-kws-zipformer-gigaspeech-3.3M-2024-01-01; this CoreML bundle matches its encoder / decoder / joiner outputs within FP16 tolerance (≤1e-3 on encoder, ≤1e-4 on decoder, ≤1e-3 on joiner).

Links

• speech-swift — Apple SDK
• soniqo.audio — website
• blog