---
license: cc-by-4.0
library_name: coreml
tags:
- coreml
- apple-neural-engine
- ane
- asr
- parakeet
- conformer
base_model: nvidia/parakeet-tdt-0.6b-v3
---

# Parakeet-TDT-0.6b-v3 Conformer encoder — CoreML / Apple Neural Engine

The **Conformer encoder** of `nvidia/parakeet-tdt-0.6b-v3`, converted to CoreML so it runs
on the **Apple Neural Engine (ANE)**. Pair it with the MLX TDT decoder in
[mlx-audio-swift](https://github.com/Blaizzy/mlx-audio-swift): the encoder runs on the ANE
while decoding stays on the GPU/CPU.

This is the **encoder only** — you still need the MLX model
(`beshkenadze/parakeet-tdt-0.6b-v3-mlx-fp16`) for the decoder.

## Format

- CoreML **MLProgram**, fp16 weights, **fp32 I/O**, `CPU_AND_NE`.
- **Fixed input shape**: `features [1, 128, 1000]` (1000 mel frames ≈ 10 s) → `encoded
  [1, 1024, 125]`. A fixed shape is required for ANE residency (a dynamic axis drops it
  to 0%); chunks are padded to 1000 frames and the output cropped back.

## Usage (mlx-audio-swift)

```bash
mlx-audio-swift-stt \
  --model beshkenadze/parakeet-tdt-0.6b-v3-mlx-fp16 \
  --audio input.wav --output-path out \
  --coreml-encoder parakeet_enc_0.6b_v3.mlpackage \
  --chunk-duration 9.95
```

Keep `--chunk-duration ≤ 10s` (the fixed encoder length).

## Measured (M1 Max, TED-LIUM 3 talk, 20.8 min)

| | all-MLX | hybrid (this encoder) |
|---|---|---|
| ANE residency | — | **100%** (0 graph interruptions) |
| WER vs reference | 7.28% | **7.11%** (agreement 1.07%) |
| RTF (Swift release) | ~95× | **~131×** (~1.38×) |
| GPU power | 17.3 W | **3.0 W** (÷5.8) |

The transcript is reproduced ~1:1; CoreML-fp16 is actually closer to fp32 than the
shipped MLX-bf16 encoder. Uses only public `MLModel` + `MLComputeUnits` APIs.

## Conversion

Produced with the converter in
[mlx-audio-swift `tools/coreml-ane/`](https://github.com/beshkenadze/mlx-audio-swift):
NeMo encoder → `torch.jit.trace` (fixed shape) → `coremltools` (fp16 MLProgram,
`CPU_AND_NE`).

License follows the base model (`nvidia/parakeet-tdt-0.6b-v3`, CC-BY-4.0).