SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
-
Updated
Oct 19, 2024 - Python
SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
A collections of audio codecs with a standardized API
SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling
unofficial implementation of the High Fidelity Neural Audio Compression
Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'
Experiments sonifying frame-level encodecmae features and encodecmae summary vectors using generative audio models.
FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.
A TTS app where you can clone the voices of any person you wish.
Add a description, image, and links to the encodec topic page so that developers can more easily learn about it.
To associate your repository with the encodec topic, visit your repo's landing page and select "manage topics."