---
language:
  - nb
  - no
license: apache-2.0
library_name: mlx
tags:
  - automatic-speech-recognition
  - whisper
  - mlx
  - nb
  - no
base_model: NbAiLab/nb-whisper-medium
pipeline_tag: automatic-speech-recognition
---

# nb-whisper-medium (MLX, float16)

MLX conversion of [NbAiLab/nb-whisper-medium](https://huggingface.co/NbAiLab/nb-whisper-medium) for fast inference on Apple Silicon via [mlx-whisper](https://github.com/ml-explore/mlx-examples/tree/main/whisper).

Converted with `mlx-examples/whisper/convert.py` at `float16` precision.

## Usage

```bash
pip install mlx-whisper
mlx_whisper audio_file.mp3 --model FredrikKarlssonSpeech/nb-whisper-medium-mlx
```

```python
import mlx_whisper
result = mlx_whisper.transcribe("audio_file.mp3", path_or_hf_repo="FredrikKarlssonSpeech/nb-whisper-medium-mlx")
print(result["text"])
```