SNAC ๐ฟ
Multi-Scale Neural Audio Codec (SNAC) compressess audio into discrete codes at a low bitrate.
๐ This model was primarily trained on music data, and its recommended use case is music (and SFX) generation. See below for other pretrained models.
๐ 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).
Model | Bitrate | Sample Rate | Params | Recommended use case |
---|---|---|---|---|
hubertsiuzdak/snac_24khz | 0.98 kbps | 24 kHz | 19.8 M | ๐ฃ๏ธ Speech |
hubertsiuzdak/snac_32khz (this model) | 1.9 kbps | 32 kHz | 54.5 M | ๐ธ Music / Sound Effects |
hubertsiuzdak/snac_44khz | 2.6 kbps | 44 kHz | 54.5 M | ๐ธ Music / Sound Effects |
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)
โ ๏ธ 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.
- Downloads last month
- 2