Downloads · 30 days
239
23% of all-time downloads
majentik/fishaudio-s2-pro-MLX-4bit
fishaudio-s2-pro-MLX-4bit is a text-to-speech model from majentik. Use it when you need text read aloud. It is set up for mlx-audio. The card lists the license as other.
MLX 4-bit quantization of fishaudio/s2-pro, produced with mlx-audio on Apple Silicon.
Downloads · 30 days
239
23% of all-time downloads
All-time downloads
1K
Public
Parameters
4.6B
4.4 GB on disk
Likes
6
Public
Click a slice to open those files.
.safetensors2.6 GB · 58%
How the weights are stored.
U324.6B · 100%
From the Hugging Face model README
MLX 4-bit quantization of fishaudio/s2-pro, produced with mlx-audio on Apple Silicon.
Built with Fish Audio.
Converted directly from fishaudio/s2-pro bf16 safetensors via python -m mlx_audio.convert ... -q --q-bits 4 --q-group-size 64. The codec.pth audio decoder, tokenizer, and chat template are preserved alongside the quantized LLM weights.
fish_qwen3_omni — a Qwen3-based decoder-only LLM that emits audio tokens consumed by the codec.pth DualAR codec. The text side is quantized; the codec is kept as-is.
from mlx_audio.tts import load
model = load("majentik/fishaudio-s2-pro-MLX-4bit")
audio = model.generate(
text="Hello, this is a test of Fish S2 Pro at 4-bit MLX.",
voice="en_default",
)
Fish S2 Pro supports zero-shot voice cloning from a reference audio sample; see the base model card for the reference-conditioning API.
This model is a derivative work of Fish Audio S2 Pro, licensed under the Fish Audio Research License.
[email protected].See LICENSE.md and NOTICE files bundled with this repository.
English, Chinese, Japanese, Korean, Spanish, Portuguese, Arabic, Russian, French, German (per base model card).