---
library_name: mlx
---

# whisper-large-v3-turbo-german-f16
This model was converted to MLX format from primeline/whisper-large-v3-turbo-german

made this with a [custom script for converting safetensor whisper models](https://github.com/CrispStrobe/mlx-examples/blob/main/whisper/convert_safetensors.py). 

it is in float16, works well, quantization should also be possible, untested yet.

## Use with MLX
```bash
git clone https://github.com/ml-explore/mlx-examples.git
cd mlx-examples/whisper/
pip install -r requirements.txt
```

```python
import mlx_whisper
result = mlx_whisper.transcribe("test.mp3", path_or_hf_repo="mlx-community/whisper-large-v3-turbo-german-f16")
print(result)
```