This repository contains training and inference scripts for the Descript Audio Codec (.dac), a high fidelity general neural audio codec, introduced in the paper titled High-Fidelity Audio Compression with Improved RVQGAN.
📈 Demo Site
⚙ Model Weights
👉 With Descript Audio Codec, you can compress 44.1 KHz audio into discrete codes at a low 8 kbps bitrate.
🤌 That's approximately 90x compression while maintaining exceptional fidelity and minimizing artifacts.
💪 Our universal model works on all domains (speech, environment, music, etc.), making it widely applicable to generative modeling of all audio.
👌 It can be used as a drop-in replacement for EnCodec for all audio language modeling applications (such as AudioLMs, MusicLMs, MusicGen, etc.)
pip install descript-audio-codec
OR
pip install git+https://github.com/descriptinc/descript-audio-codec
Weights are released as part of this repo under MIT license.
We release weights for models that can natively support 16 kHz, 24kHz, and 44.1kHz sampling rates.
Weights are automatically downloaded when you first run encode or decode command. You can cache them using one of the following commands
python3 -m dac download # downloads the default 44kHz variant
python3 -m dac download --model_type 44khz # downloads the 44kHz variant
python3 -m dac download --model_type 24khz # downloads the 24kHz variant
python3 -m dac download --model_type 16khz # downloads the 16kHz variantWe provide a Dockerfile that installs all required dependencies for encoding and decoding. The build process caches the default model weights inside the image. This allows the image to be used without an internet connection. Please refer to instructions below.
python3 -m dac encode /path/to/input --output /path/to/output/codes
This command will create .dac files with the same name as the input files.
It will also preserve the directory structure relative to input root and
re-create it in the output directory. Please use python -m dac encode --help
for more options.
python3 -m dac decode /path/to/output/codes --output /path/to/reconstructed_input
This command will create .wav files with the same name as the input files.
It will also preserve the directory structure relative to input root and
re-create it in the output directory. Please use python -m dac decode --help
for more options.
import dac
from dac.utils import load_model
from dac.model import DAC
from dac.utils.encode import process as encode
from dac.utils.decode import process as decode
from audiotools import AudioSignal
# Init an empty model
model = DAC()
# Load compatible pre-trained model
model = load_model(tag="latest", model_type="44khz")
model.eval()
model.to('cuda')
# Load audio signal file
signal = AudioSignal('input.wav')
# Encode audio signal
encoded_out = encode(signal, 'cuda', model)
# Decode audio signal
recon = decode(encoded_out, 'cuda', model, preserve_sample_rate=True)
# Write to file
recon.write('recon.wav')We provide a dockerfile to build a docker image with all the necessary dependencies.
-
Building the image.
docker build -t dac . -
Using the image.
Usage on CPU:
docker run dac <command>Usage on GPU:
docker run --gpus=all dac <command><command>can be one of the compression and reconstruction commands listed above. For example, if you want to run compression,docker run --gpus=all dac python3 -m dac encode ...
The baseline model configuration can be trained using the following commands.
Please install the correct dependencies
pip install -e ".[dev]"
export CUDA_VISIBLE_DEVICES=0
python scripts/train.py --args.load conf/ablations/baseline.yml --save_path runs/baseline/
export CUDA_VISIBLE_DEVICES=0,1
torchrun --nproc_per_node gpu scripts/train.py --args.load conf/ablations/baseline.yml --save_path runs/baseline/
We provide two test scripts to test CLI + training functionality. Please make sure that the trainig pre-requisites are satisfied before launching these tests. To launch these tests please run
python -m pytest tests
