Audio-to-Audio
Transformers
Safetensors
qwen2
audio
speech
s2s
multimodal
diffusion
non-autoregressive
text-generation-inference
Instructions to use Stephen-Lee/TtT-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Stephen-Lee/TtT-3B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, Qwen2ForARDiffLM tokenizer = AutoTokenizer.from_pretrained("Stephen-Lee/TtT-3B") model = Qwen2ForARDiffLM.from_pretrained("Stephen-Lee/TtT-3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from Stephen-Lee/TtT-3B: direct link, hf CLI and curl.
- Browser
- Download file 14.6 MB
-
https://huggingface.co/Stephen-Lee/TtT-3B/resolve/main/tokenizer.json
- Command line
-
hf download hf://Stephen-Lee/TtT-3B/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/Stephen-Lee/TtT-3B/resolve/main/tokenizer.json
14.6 MB
- Xet hash:
- b2c35b3e0fad1c4fe2228d50dc85d247620ceb8b92bc4c6cf272a8f57ad5f48f
- Size of remote file:
- 14.6 MB
- SHA256:
- 98396732f9e8e0142620b4dea70b2c62d0b2ade1a1a997af0b8848050eb69a95
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.