Downloads · 30 days
44
12% of all-time downloads
kb-whisper-small-mlx
Leonidng/kb-whisper-small-mlx
kb-whisper-small-mlx is a machine learning model from Leonidng. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx-whisper. The card lists the license as mit.
MLX-converted version of KBLab/kb-whisper-small for Apple Silicon.
All-time downloads
353
Public
Repo size
481 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors481 MB · 100%
At a glance
- Library
- mlx-whisper
- License
- mit
- Model type
- whisper
- Access
- Public
- Created
- Mar 8, 2026
- Updated
- Mar 8, 2026
- SHA
- 9e6bbf71
Base models
Model card
From the Hugging Face model README
KB Whisper Small — MLX
MLX-converted version of KBLab/kb-whisper-small for Apple Silicon.
Usage
import mlx_whisper
result = mlx_whisper.transcribe(
"audio.wav",
path_or_hf_repo="Leonidng/kb-whisper-small-mlx",
language="sv",
)
print(result["text"])
Model details
- Base model: KBLab/kb-whisper-small (Swedish fine-tuned Whisper small)
- Format: MLX (float16 safetensors)
- Size: ~459 MB
- Conversion: Converted using mlx-examples/whisper/convert.py
KBLab's Swedish fine-tune of Whisper small outperforms OpenAI's whisper-large-v3 on Swedish benchmarks while being significantly smaller and faster.
- Library
- mlx-whisper
- Type
- whisper
- License
- mit
- Languages
- sv
- Created
- Mar 8, 2026
- Updated
- Mar 8, 2026