README.md

metadata

library_name: transformers
tags:
  - DAC
  - Audio
license: mit

This repository offers 16khzDAC with 9 codebooks and 8kbps bitrate.

For integration into ParlerTTS, you first need to install the Parler-TTS library with (to do once):

pip install git+https://github.com/huggingface/parler-tts.git

Descript Audio Codec (.dac): High-Fidelity Audio Compression with Improved RVQGAN

This repository is a wrapper around the original Descript Audio Codec model, a high fidelity general neural audio codec, introduced in the paper titled High-Fidelity Audio Compression with Improved RVQGAN.

It is designed to be used as a drop-in replacement of the transformers implementation of Encodec, so that architectures that use Encodec can also be trained with DAC instead. The Parler-TTS library is an example of how to use DAC to train high-quality TTS models.