qwen3-asr-1.7b-bf16-mlx

Qwen3-ASR-1.7B — MLX (bf16)

MLX-native bf16 conversion of Qwen3-ASR-1.7B for local automatic speech recognition on Apple Silicon — English, Chinese, and mixed Chinese/English. It runs through the mlx-speech runtime with no PyTorch and no cloud API at inference time. Weights ship as plain .safetensors.

This is the unquantized reference build. Most users should prefer the int8 build — it matched this build's transcripts on our English test clips. Use bf16 when you want the full-precision baseline (e.g. to compare quantization quality yourself).

Model Details

• Developed by: App Automaton
• Upstream model: Qwen/Qwen3-ASR-1.7B (code: QwenLM/Qwen3-ASR)
• Task: automatic speech recognition — English, Chinese, and mixed Chinese/English (upstream supports more languages; the mlx-speech v0 path validates en/zh/mixed)
• Precision: bf16 — MLX format port; keys are remapped to the MLX module tree and audio Conv2D weights transposed to MLX layout
• Runtime: MLX on Apple Silicon
• Input: 16 kHz mono audio

Variants

How to Get Started

Install mlx-speech, then load by alias (downloads on first use):

import mlx_speech

asr = mlx_speech.asr.load("qwen3-asr-1.7b-bf16")
result = asr.generate("speech.wav")               # language=None auto-detects
print(result.language, result.text)

# For mixed Chinese/English, forcing Chinese preserves Chinese characters best:
result = asr.generate("mixed-speech.wav", language="Chinese")

mlx-speech asr --model qwen3-asr-1.7b-bf16 --audio speech.wav

Or download the weights once and load by local path:

hf download appautomaton/qwen3-asr-1.7b-bf16-mlx \
  --local-dir models/qwen3_asr_1_7b/mlx-bf16

asr = mlx_speech.asr.load("models/qwen3_asr_1_7b/mlx-bf16")

Notes

• This repo contains the MLX runtime artifact only (no PyTorch checkpoint).
• v0 is single-pass offline ASR; streaming, timestamps, and long-audio chunking are deferred.
• For a smaller download, use the int8 build.

Links

• Source code: appautomaton/mlx-speech
• Project page: appautomaton.com/mlx-speech
• Default int8 variant: appautomaton/qwen3-asr-1.7b-int8-mlx
• More from App Automaton: Project · GitHub · Hugging Face

License

Apache 2.0, following the upstream Qwen3-ASR release. Refer to the original Qwen release for current terms.