Instructions to use Marvis-AI/marvis-tts-250m-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Marvis-AI/marvis-tts-250m-v0.2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="Marvis-AI/marvis-tts-250m-v0.2")# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("Marvis-AI/marvis-tts-250m-v0.2") model = AutoModelForTextToWaveform.from_pretrained("Marvis-AI/marvis-tts-250m-v0.2") - MLX
How to use Marvis-AI/marvis-tts-250m-v0.2 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir marvis-tts-250m-v0.2 Marvis-AI/marvis-tts-250m-v0.2
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
pruned csm
#2
by MrDragonFox - opened
this is very much a pruned csm as you can see in the config.json
MrDragonFox changed discussion status to closed
It shares an underlying architecture but is trained from scratch on permissively-licensed data, fwiw.