Text-to-Speech
Transformers
Safetensors
qwen2
text-generation
Speech-Tokenizer
Text-to-Speech
text-generation-inference
Instructions to use amphion/TaDiCodec-TTS-AR-Qwen2.5-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amphion/TaDiCodec-TTS-AR-Qwen2.5-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="amphion/TaDiCodec-TTS-AR-Qwen2.5-3B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("amphion/TaDiCodec-TTS-AR-Qwen2.5-3B") model = AutoModelForCausalLM.from_pretrained("amphion/TaDiCodec-TTS-AR-Qwen2.5-3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add `library_name: transformers` to model card metadata
#1
by nielsr HF Staff - opened
This PR enhances the model card by adding the library_name: transformers metadata tag.
This addition is justified by:
- The
config.jsonindicatingQwen2ForCausalLMas the architecture andtransformers_version: "4.40.1". - The "Acknowledgments" section in the README explicitly stating that "NAR Llama-style transformers is built upon transformers".
Adding this metadata will enable an automated, pre-defined code snippet on the model page, showcasing how to easily load and use the model with the 🤗 Transformers library.
LGTM!
Hecheng0625 changed pull request status to merged