Text-to-Speech
Safetensors
MLX
mlx-audio
fish_qwen3_omni
speech
speech-generation
voice-cloning
tts
fish-audio
s2-pro
quantized
4bit
4-bit precision
Instructions to use majentik/fishaudio-s2-pro-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use majentik/fishaudio-s2-pro-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir fishaudio-s2-pro-MLX-4bit majentik/fishaudio-s2-pro-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Xet hash:
- 708d4c6aba8134c5fb74878b268f89f0df22f72ff1a38e0db89a159e85d4ab0f
- Size of remote file:
- 1.87 GB
- SHA256:
- 74fc41c5a7151c6f350af8bd7e5d6e3accfcc7f3dfbfac23afd35af07052bb2f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.