Downloads · 30 days
44
16% of all-time downloads
whisper-medium-4bit
mlx-community/whisper-medium-4bit
whisper-medium-4bit is a automatic speech recognition model from mlx-community. Use it when you need speech turned into text. It is set up for mlx-audio-plus. The card lists the license as apache-2.0.
This model was converted to MLX format from openai/whisper-medium using mlx-audio-plus version 0.1.4.
All-time downloads
282
Public
Parameters
762M
871 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors436 MB · 100%
Parameter types
How the weights are stored.
U32758M · 99%
Base models
Model card
From the Hugging Face model README
mlx-community/whisper-medium-4bit
This model was converted to MLX format from openai/whisper-medium using mlx-audio-plus version 0.1.4.
Use with mlx-audio-plus
pip install -U mlx-audio-plus
Command line
mlx_audio.stt --model mlx-community/whisper-medium-4bit --audio audio.mp3
Python
from mlx_audio.stt import transcribe
result = transcribe(
audio="audio.mp3",
model="mlx-community/whisper-medium-4bit",
)
print(result["text"])
- Task
- Automatic Speech Recognition
- Library
- mlx-audio-plus
- Type
- whisper
- License
- apache-2.0
- Created
- Dec 14, 2025
- Updated
- Dec 15, 2025