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

aoiandroid/qwen3-asr-0.6b-coreml

Qwen3-ASR 0.6B CoreML

Model Variants

Features

Benchmarks (M4 Pro)

Usage with FluidAudio

aoiandroid/
qwen3-asr-0.6b-coreml