Dan Lyth's starred repositories
ml-engineering
Machine Learning Engineering Open Book
WhisperSpeech
An Open Source text-to-speech system built by inverting Whisper.
musiclm-pytorch
Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch
pytorch-optimizer
torch-optimizer -- collection of optimizers for Pytorch
audiolm-pytorch
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
audio-diffusion-pytorch
Audio generation using diffusion models, in PyTorch.
audiomentations
A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.
Notion-to-Obsidian-Converter
Converts exported Notion notes to work with Obsidian.
WavAugment
A library for speech data augmentation in time-domain
GigaSpeech
Large, modern dataset for speech recognition
textlesslib
Library for Textless Spoken Language Processing
diffwave-sashimi
Implementation of DiffWave and SaShiMi audio generation models
notion-zotero
Create a Notion collection, synced with Zotero.
Voice-conversion-evaluation
An evaluation toolkit for voice conversion models.
musicgen_trainer
simple trainer for musicgen/audiocraft