knoveleng/aishell3-mandarin
Viewer • Updated • 88k • 851
How to use thucdangvan020999/polyglot-lion-0.6b-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir polyglot-lion-0.6b-bf16 thucdangvan020999/polyglot-lion-0.6b-bf16
This model was converted to MLX format from knoveleng/polyglot-lion-0.6b using mlx-audio version 0.4.3.
Refer to the original model card for more details on the model.
pip install -U mlx-audio
python -m mlx_audio.stt.generate --model thucdangvan020999/polyglot-lion-0.6b-bf16 --audio "audio.wav"
from mlx_audio.stt.utils import load_model
from mlx_audio.stt.generate import generate_transcription
model = load_model("thucdangvan020999/polyglot-lion-0.6b-bf16")
transcription = generate_transcription(
model=model,
audio_path="path_to_audio.wav",
output_path="path_to_output.txt",
format="txt",
verbose=True,
)
print(transcription.text)
Quantized
Base model
Qwen/Qwen3-ASR-0.6B