Text-to-Speech
Transformers
Safetensors
fish_qwen3_omni
instruction-following
multilingual
quantized
fp8
comfyui
comfy
multi-turn
multi-speaker
sglang
Instructions to use drbaph/s2-pro-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use drbaph/s2-pro-fp8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="drbaph/s2-pro-fp8")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("drbaph/s2-pro-fp8", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add base_model and library_name metadata
#1
by nielsr HF Staff - opened
Hi! I'm Niels from the Hugging Face community science team.
This PR improves the model card by:
- Adding
base_model: fishaudio/s2-proto the metadata to link this quantized version to the original model. - Adding
library_name: transformersbased on theconfig.jsonfile. - Adding a brief summary of the Fish Audio S2 paper to provide more context for users.
- Adding relevant tags like
multi-turnandmulti-speakerbased on the technical report.
drbaph changed pull request status to merged