A collection of audio codecs with a standardized API. The following codecs are currently supported:
First of all, install Python 3.8 or later.
Clone or download and extract the repository, navigate to <path-to-repository>, open a terminal and run:
# Install the package locally in editable mode
pip install -e .[all]To use one of the available codecs in your script:
import torch
import torchaudio
from audiocodecs import Encodec
sig, sample_rate = torchaudio.load("<path-to-audio-file>")
model = Encodec(sample_rate=sample_rate, orig_sample_rate=24000, num_codebooks=8)
with torch.no_grad():
toks = model.sig_to_toks(sig)
rec_sig = model.toks_to_sig(toks)
torchaudio.save("reconstruction.wav", rec_sig, sample_rate)Reference implementations of downstream tasks using audio codecs can be found in benchmarks.