metadata
license: apache-2.0
library_name: mlx
tags:
- speech-enhancement
- audio
- mlx
MossFormer2 SE 4-bit (MLX)
48kHz speech enhancement model converted to MLX format (4-bit quantized).
Original Model
alibabasglab/MossFormer2_SE_48K
Usage
from mlx_audio.sts.models.mossformer2_se import MossFormer2SEModel
model = MossFormer2SEModel.from_pretrained("starkdmi/MossFormer2-SE-4bit")
enhanced = model.enhance("noisy.wav")
Precision Variants
- MossFormer2-SE (fp32, 211MB)
- MossFormer2-SE-fp16 (fp16, 106MB)
- MossFormer2-SE-8bit (int8, 86MB)
- MossFormer2-SE-6bit (int6, 75MB)
- MossFormer2-SE-4bit (int4, 64MB) ← this
Performance
~30x real-time on Apple M4