Qwen3-ASR-1.7B-JA-MLX-8bit

ph0ryn/Qwen3-ASR-1.7B-JA-MLX-8bit

This model was converted to MLX format from neosophie/Qwen3-ASR-1.7B-JA using mlx-audio version 0.4.3.

Refer to the original model card for more details on the model.

Use with mlx-audio

pip install -U mlx-audio

CLI Example:

python -m mlx_audio.stt.generate --model ph0ryn/Qwen3-ASR-1.7B-JA-MLX-8bit --audio "audio.wav"

Python Example:

from mlx_audio.stt.utils import load_model
from mlx_audio.stt.generate import generate_transcription

model = load_model("ph0ryn/Qwen3-ASR-1.7B-JA-MLX-8bit")
transcription = generate_transcription(
    model=model,
    audio_path="path_to_audio.wav",
    output_path="path_to_output.txt",
    format="txt",
    verbose=True,
)
print(transcription.text)