aufklarer/Qwen3-ASR-CoreML

Source: 🤗automatic-speech-recognitionapache-2.01.6 GBother✓ 18 checksumsupdated 166d ago

CommentsShare your thoughts and shape the future of sovereign AI.

@aufklarer is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @aufklarer

Files and sources

SourceAvailable on 🤗

Checksums18 recorded

TorrentNot listed

SwarmNot checked

Source revision: 8c6bc87b8785…
Witnessed: 24 Sept 2026, 00:32 UTC
Weight files: 18
Model size: 1.6 GB
Downloads · last month: 1,727
Publisher: Unclaimed

WeightsAs Hugging Face lists them. Magnet: Pirate Face lists these exact files.

Other

Weights1.6 GB
15 files
decoder_part2.mlmodelc/weights/weight.bin 376 MBencoder_fp16.mlpackage/Data/com.apple.CoreML/weights/weight.bin 373 MBdecoder_part1.mlmodelc/weights/weight.bin 220 MBencoder.mlmodelc/weights/weight.bin 187 MBencoder_int8.mlpackage/Data/com.apple.CoreML/weights/weight.bin 187 MBembedding.mlmodelc/weights/weight.bin 156 MBencoder_int4.mlpackage/Data/com.apple.CoreML/weights/weight.bin 94 MBdecoder_part1.mlmodelc/coremldata.bin 1.3 kBdecoder_part2.mlmodelc/coremldata.bin 1.3 kBencoder.mlmodelc/coremldata.bin 0.4 kBembedding.mlmodelc/coremldata.bin 0.3 kBdecoder_part1.mlmodelc/analytics/coremldata.bin 0.2 kBdecoder_part2.mlmodelc/analytics/coremldata.bin 0.2 kBembedding.mlmodelc/analytics/coremldata.bin 0.2 kBencoder.mlmodelc/analytics/coremldata.bin 0.2 kB

Qwen3-ASR-0.6B — CoreML

CoreML conversion of Qwen/Qwen3-ASR-0.6B for Apple Neural Engine.

Contains both audio encoder and text decoder for full Neural Engine inference (no GPU required).

Models

Model	Description	Quantization
`encoder.mlmodelc`	Audio encoder (mel → embeddings)	INT8 palettized
`embedding.mlmodelc`	Token embedding lookup	INT8 palettized
`decoder.mlmodelc`	Text decoder with KV cache (28 layers)	INT8 palettized
`encoder_int4.mlpackage`	Audio encoder source	INT4 palettized
`encoder_int8.mlpackage`	Audio encoder source	INT8 palettized

Usage

Full CoreML pipeline (encoder + decoder on Neural Engine):

[1;38;5;196mWelcome to Swift![0m

[1mSubcommands:[0m

[1mswift build[0m Build Swift packages [1mswift package[0m Create and work on packages [1mswift run[0m Run a program from a package [1mswift test[0m Run package tests [1mswift repl[0m Experiment with Swift code interactively

Use [1mswift --version[0m for Swift version information.

Use [1mswift --help[0m for descriptions of available options and flags.

Use [1mswift help <subcommand>[0m for more information about a subcommand.

Hybrid mode (CoreML encoder + MLX decoder on GPU):

Architecture

Audio encoder: 18-layer Whisper-style transformer (896 dim, 14 heads)
Text decoder: 28 layers, 1024 hidden, 16 heads (8 KV heads)
KV cache: Fixed 1024 tokens via CoreML MLState
Requires: macOS 15+ / iOS 18+ (full CoreML mode)

Links

Swift library: soniqo/speech-swift
Base model: Qwen/Qwen3-ASR-0.6B

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

WeightsAs Hugging Face lists them. Magnet: Pirate Face lists these exact files.

Other

Weights1.6 GB
15 files
decoder_part2.mlmodelc/weights/weight.bin 376 MBencoder_fp16.mlpackage/Data/com.apple.CoreML/weights/weight.bin 373 MBdecoder_part1.mlmodelc/weights/weight.bin 220 MBencoder.mlmodelc/weights/weight.bin 187 MBencoder_int8.mlpackage/Data/com.apple.CoreML/weights/weight.bin 187 MBembedding.mlmodelc/weights/weight.bin 156 MBencoder_int4.mlpackage/Data/com.apple.CoreML/weights/weight.bin 94 MBdecoder_part1.mlmodelc/coremldata.bin 1.3 kBdecoder_part2.mlmodelc/coremldata.bin 1.3 kBencoder.mlmodelc/coremldata.bin 0.4 kBembedding.mlmodelc/coremldata.bin 0.3 kBdecoder_part1.mlmodelc/analytics/coremldata.bin 0.2 kBdecoder_part2.mlmodelc/analytics/coremldata.bin 0.2 kBembedding.mlmodelc/analytics/coremldata.bin 0.2 kBencoder.mlmodelc/analytics/coremldata.bin 0.2 kB

Seed this model

Have the files? Submit a torrent.

Submit a torrent

Package the files with one command

Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo aufklarer/Qwen3-ASR-CoreML ./model-folder