An Open-source Streaming High-fidelity Neural Audio Codec

Vector (and Scalar) Quantization, in Pytorch

AcademiCodec: An Open Source Audio Codec Model for Academic Research

Perceptual Quality Estimator for speech and audio

FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.

Ultra-low bitrate neural audio codec (0.31~1.40 kbps) with a better semantic in the latent space.

Keras implement of Finite Scalar Quantization

Low-complexity neural image & video codec.

The open source code for LLM-Codec

Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice

Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate

A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

Awesome Neural Codec Models, Text-to-Speech Synthesizers & Speech Language Models