Instructions to use tutu0604/UltraVoice-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tutu0604/UltraVoice-SFT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="tutu0604/UltraVoice-SFT")# Load model directly from transformers import SLAM-Omni model = SLAM-Omni.from_pretrained("tutu0604/UltraVoice-SFT", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add metadata (pipeline tag, library name) and improve model card content
#1
by nielsr HF Staff - opened
This PR enhances the model card by:
- Adding
pipeline_tag: text-to-speechto improve discoverability on the Hugging Face Hub. - Adding
library_name: transformersto enable the automated "Use in Transformers" widget, providing a convenient code snippet for users. Evidence fortransformerscompatibility is found in the tokenizer configuration files andadapter_config.json(PEFT via LoRA is commonly used withtransformers). - Updating the paper link badge from arXiv to the official Hugging Face paper page.
- Including the full abstract from the paper for more complete information.
- Incorporating the
π’ Newsandπ Datasetsections from the project's GitHub README to provide a more comprehensive overview. - Adding a dedicated
π§© Model Checkpointssection with direct links to the Hugging Face Hub resources. - Ensuring consistent use of emojis in section titles for better readability.
Please review and merge if these improvements align with the project's goals.
tutu0604 changed pull request status to merged