Instructions to use mlx-community/whisper-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/whisper-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mlx-community/whisper-tiny")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mlx-community/whisper-tiny", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add model weights in safetensors format
#2
by depasquale - opened
@lawrencewu , I've converted the weights to safetensors for use in Swift apps, which cannot open the .npz format. I'd appreciate it if you could merge this so that people can use Whisper in mlx-swift-audio.