Descript Audio Codec — MLX

This model is reshaped for MLX from the original weights and is designed for use with descript-mlx

Installation

pip install descript-mlx

Usage

You can load a pretrained model from Python like this:

import mlx.core as mx

from descript_mlx import DAC

dac = DAC.from_pretrained("24khz")
audio = mx.array(...)

# encode into latents and codes
z, codes, latents, commitment_loss, codebook_loss = dac.encode(audio)

# reconstruct from latents/codes to audio
reconstucted_audio = dac.decode(z)

# compress audio to a DAC file
dac_file = dac.compress(audio)
dac_file.save("/path/to/file.dac")

# decompress audio from a DAC file
reconstructed_audio = dac.decompress("/path/to/file.dac")
Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
74.7M params
Tensor type
F32
·
Inference API
Unable to determine this model’s pipeline type. Check the docs .