FluidInference/qwen3-asr-0.6b-coreml

license: apache-2.0 language:

• —en
• —zh
• —ja
• —ko
• —vi
• —th
• —id
• —ms
• —hi
• —ar
• —tr
• —ru
• —de
• —fr
• —es
• —multilingual tags:
• —speech-recognition
• —asr
• —coreml
• —apple
• —ios
• —macos
• —qwen
• —audio libraryname: coreml pipelinetag: automatic-speech-recognition base_model: Qwen/Qwen3-ASR-0.6B ---

Qwen3-ASR 0.6B CoreML

Core ML conversion of Qwen/Qwen3-ASR-0.6B for on-device speech recognition on Apple platforms (iOS/macOS).

Model Variants

Features

• —30+ languages including English, Chinese, Japanese, Korean, and more
• —On-device inference - no internet required
• —Autoregressive decoder with KV-cache support
• —Processes audio in 1-second chunks (100 mel frames)

Benchmarks (M4 Pro)

Official PyTorch model: 2.11% WER on LibriSpeech test-clean

Usage with FluidAudio

import FluidAudio

let manager = Qwen3AsrManager()
try await manager.loadModels()

let samples = try AudioConverter().resampleAudioFile(path: "audio.wav")
let transcript = try await manager.transcribe(
    audioSamples: samples,
    language: "en",
    maxNewTokens: 512
)
print(transcript)

Model Architecture

• —Encoder: Audio encoder (Whisper-style mel spectrogram input)
• —Decoder: 28-layer transformer decoder with 1024 hidden size
• —Tokenizer: Qwen tokenizer with special ASR tokens

License

Apache 2.0 - Same as the original Qwen3-ASR model.

Credits

• —Original model: https://huggingface.co/Qwen/Qwen3-ASR-0.6B by Alibaba Qwen Team
• —Paper: https://arxiv.org/abs/2601.21337
• —CoreML conversion: https://github.com/FluidInference/FluidAudio

Citation

@article{qwen3asr, title={Qwen3-ASR Technical Report}, author={Qwen Team}, journal={arXiv preprint arXiv:2601.21337}, year={2025} }

For the HuggingFace metadata UI, fill in:

• —License: Apache 2.0
• —Base model: Qwen/Qwen3-ASR-0.6B
• —Pipeline: automatic-speech-recognition
• —Library: coreml
• —Languages: en, zh, ja, ko, + others