Downloads · 30 days
18
37% of all-time downloads
nb-whisper-medium-mlx-4bit
FredrikKarlssonSpeech/nb-whisper-medium-mlx-4bit
nb-whisper-medium-mlx-4bit is a automatic speech recognition model from FredrikKarlssonSpeech. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as apache-2.0.
MLX conversion of NbAiLab/nb-whisper-medium for fast inference on Apple Silicon via mlx-whisper.
All-time downloads
49
Public
Repo size
436 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors436 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026
- SHA
- 66a0e251
Base models
Model card
From the Hugging Face model README
nb-whisper-medium (MLX, 4-bit quantized)
MLX conversion of NbAiLab/nb-whisper-medium for fast inference on Apple Silicon via mlx-whisper.
Converted with mlx-examples/whisper/convert.py at 4-bit quantized precision.
Usage
pip install mlx-whisper
mlx_whisper audio_file.mp3 --model FredrikKarlssonSpeech/nb-whisper-medium-mlx-4bit
import mlx_whisper
result = mlx_whisper.transcribe("audio_file.mp3", path_or_hf_repo="FredrikKarlssonSpeech/nb-whisper-medium-mlx-4bit")
print(result["text"])
- Task
- Automatic Speech Recognition
- Library
- mlx
- Type
- whisper
- License
- apache-2.0
- Languages
- nb, no
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026