aufklarer/Parakeet-TDT-v3-CoreML-INT8-iOS

Parakeet TDT v3 — CoreML INT8 (iOS)

CoreML INT8 conversion of NVIDIA Parakeet-TDT 0.6B v2 optimized for iOS deployment on Neural Engine. Encoder uses EnumeratedShapes for variable-length audio input.

Models

Model	Description	Compute	Quantization
encoder.mlmodelc	FastConformer encoder (24L, 1024 hidden)	Neural Engine	INT8 palettized
decoder.mlmodelc	LSTM prediction network (2L, 640 hidden)	Neural Engine	FP16

Usage

Used by speech-swift ParakeetASR module:

let model = try await ParakeetASRModel.fromPretrained()
let text = try model.transcribeAudio(samples, sampleRate: 16000)

---

• Guide: soniqo.audio/guides/parakeet
• Docs: soniqo.audio
• GitHub: soniqo/speech-swift