Instructions to use mlx-community/S3TokenizerV2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/S3TokenizerV2 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/S3TokenizerV2 --local-dir S3TokenizerV2
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commercial and non-commercial licensing clarification for S3TokenizerV2
Hello MLX Community,
I am developing SpeekBox, a macOS text-to-speech application supporting German, Greek and English.
SpeekBox uses the MLX-converted S3TokenizerV2 model, downloaded from Hugging Face during the application's initial setup.
Model: mlx-community/S3TokenizerV2
Revision: e0c9886f0e1c35ae85b1f27277416fb19fc72bec
I would like to release SpeekBox as a free application, with the possibility of commercial distribution in the future.
Could you please clarify:
- What is the exact source of the S3TokenizerV2 weights used in this MLX conversion?
- Under which license are these converted weights distributed?
- Is their use permitted in a free, publicly distributed macOS application?
- Would commercial use also be permitted?
- Are there any additional attribution or licensing requirements?
SpeekBox does not bundle the model weights; users download them during the initial setup.
If the original model owners must provide licensing permission, could you please point me to the appropriate contact?
Thank you very much for your work and support!
Best regards,
Theo
SpeekBox Developer