SNAC 🍿

Multi-Scale Neural Audio Codec (SNAC) compressess audio into discrete codes at a low bitrate.

👉 This model was primarily trained on music data, and its recommended use case is music (and SFX) generation. See below for other pretrained models.

🔗 GitHub repository: https://github.com/hubertsiuzdak/snac/

Overview

SNAC encodes audio into hierarchical tokens similarly to SoundStream, EnCodec, and DAC. However, SNAC introduces a simple change where coarse tokens are sampled less frequently, covering a broader time span.

This model compresses 32 kHz audio into discrete codes at a 1.9 kbps bitrate. It uses 4 RVQ levels with token rates of 10, 21, 42, and 83 Hz.

Pretrained models

Currently, all models support only single audio channel (mono).

Usage

Install it using:

pip install snac

To encode (and decode) audio with SNAC in Python, use the following code:

import torch
from snac import SNAC

model = SNAC.from_pretrained("hubertsiuzdak/snac_32khz").eval().cuda()
audio = torch.randn(1, 1, 32000).cuda()  # B, 1, T

with torch.inference_mode():
    codes = model.encode(audio)
    audio_hat = model.decode(codes)

You can also encode and reconstruct in a single call:

with torch.inference_mode():
    audio_hat, codes = model(audio)

⚠️ Note that codes is a list of token sequences of variable lengths, each corresponding to a different temporal resolution.

>>> [code.shape[1] for code in codes]
[12, 24, 48, 96]

Acknowledgements

Module definitions are adapted from the Descript Audio Codec.