Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

[official] PyTorch implementation of TimeVQVAE-AD, a time series anomaly detection model.

Models and code for RepCodec: A Speech Representation Codec for Speech Tokenization

Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'

Foundational model for human-like, expressive TTS

End-to-End Speech Processing Toolkit

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

[ICML 2024 Oral] Official repository of the SparseTSF paper: "SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters". This work is developed by the Lab of Professor Weiwei Lin (l…

MLX: An array framework for Apple silicon

HumanML3D: A large and diverse 3d human motion-language dataset.

Official implementation of "MoMask: Generative Masked Modeling of 3D Human Motions (CVPR2024)"

Single Motion Diffusion Model

The implementation of "TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning"

Repository for training models for music source separation.

This is an official implementation of "ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis" (ICLR 2024 Spotlight), https://openreview.net/forum?id=vpJMJerXHU

The official implementation of LIFT (ICLR'24). Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators.

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

Code release for "Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors" (NeurIPS 2023), https://arxiv.org/abs/2305.18803

Unofficial implementation of iTransformer - SOTA Time Series Forecasting using Attention networks, out of Tsinghua / Ant group

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Code for SpaceTime 🌌⏱️. Proposed in Effectively Modeling Time Series with Simple Discrete State Spaces, ICLR 2023.

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

Official implementation of our ICLR 2023 paper "Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting"

Instruct-tune LLaMA on consumer hardware

Let ChatGPT teach your own chatbot in hours with a single GPU!