Audio Codecs

A collection of audio codecs with a standardized API. The following codecs are currently supported:

• DAC
• EnCodec
• EnCodec + Vocos
• Mimi
• SemantiCodec
• SpeechTokenizer
• WavLM k-means
• WavTokenizer

---

🛠️️ Installation

From source

First of all, install Python 3.8 or later. Open a terminal and run:

pip install git+https://github.com/lucadellalib/audio-codecs.git@main

---

▶️ Quickstart

To use one of the available codecs in your script:

import torch
import torchaudio
from audio_codecs 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)

---

📧 Contact

luca.dellalib@gmail.com

---