中文Sign up

aufklarer/Qwen3-ASR-0.6B-MLX-8bit

🤗 Hugging Face sourceapache-2.0782M params1.6 GBsafetensors✓ 1 checksumupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo aufklarer/Qwen3-ASR-0.6B-MLX-8bit ./model-folder
Needs a seeder →

mlx-community/Qwen3-ASR-0.6B-8bit

This model was converted to MLX format from Qwen/Qwen3-ASR-0.6B using mlx-audio version 0.3.1.

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 mlx-community/Qwen3-ASR-0.6B-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("mlx-community/Qwen3-ASR-0.6B-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)