Text-to-Speech
Transformers
Safetensors
fish_qwen3_omni
instruction-following
multilingual
quantized
fp8
comfyui
comfy
multi-turn
multi-speaker
sglang
Instructions to use Benjonson/s2-pro-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Benjonson/s2-pro-fp8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Benjonson/s2-pro-fp8")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Benjonson/s2-pro-fp8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model.safetensors from Benjonson/s2-pro-fp8: direct link, hf CLI and curl.
- Browser
- Download file 6.16 GB
-
https://huggingface.co/Benjonson/s2-pro-fp8/resolve/main/model.safetensors
- Command line
-
hf download hf://Benjonson/s2-pro-fp8/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/Benjonson/s2-pro-fp8/resolve/main/model.safetensors
6.16 GB
- Xet hash:
- 42f6bc12092c352fa890cb1d16b514c65738d9531b3a6b1d1c5a184c6b26870f
- Size of remote file:
- 6.16 GB
- SHA256:
- 9b07bb7973109f59a013708858e2bec613582e77452f1cf451384f63ddcc1621
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.