📋 NotebookMLX - An Open Source version of NotebookLM (Ported NotebookLlama)

VAE modified from Descript Audio Codec, which replaces the RVQ with VAE

Explorations into improving ViTArc with Slot Attention

Collection of Open Source Speech Data

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS (E2 TTS) in MLX

Train VAE like a boss

MLX: An array framework for Apple silicon

SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

Explorations into some recent techniques surrounding speculative decoding