Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach

Generation and evaluation of synthetic time series datasets (also, augmentations, visualizations, a collection of popular datasets) NeurIPS'24

A Foundation Model for Industrial Signal Comprehensive Representation

This is official implementation of the PEFT-MuTS framework.

Chronos: Pretrained Models for Time Series Forecasting

[ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"

A collection of datasets for RUL estimation as Lightning Data Modules.

Try X-Dub to sync any character in a video with any audio you like | Official repository for "From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping"

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.

A Benchmark for Evaluating Representation of M5 Industrial Signals

用于预测性维护与健康管理的大型语言模型（故障诊断大模型；剩余使用寿命预测大模型）

PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning

MiMo-Audio: Audio Language Models are Few-Shot Learners

[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"

Official code, datasets and checkpoints for "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024) and subsequent works

Papers and datasets for Vibration Analysis

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

[NeurIPS 2025] Benchmark data and code for MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling

Machine Learning applied to sound

Unified automatic quality assessment for speech, music, and sound.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Open rotating mechanical fault datasets (开源旋转机械故障数据集整理)

A benchmark fault diagnosis dataset comprises vibration data collected from a gearbox under variable working conditions with intentionally induced faults, encompassing diverse fault severities and …

Benchmark popular audio i/o packages

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"

PSELDNets: Pre-trained Neural Networks on Large-scale Synthetic Datasets for Sound Event Localization and Detection

Masked Modeling Duo: Towards a Universal Audio Pre-training Framework

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