Source code and complementary material for "Keep what you need : extracting efficient subnetworks from large audio representation models".

Updated list of public BitTorrent trackers

Free, open source crypto trading bot

VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment

Unofficial implementation of "Simplifying, Stabilizing & Scaling Continuous-Time Consistency Models" for MNIST

MoBA: Mixture of Block Attention for Long-Context LLMs

verl: Volcano Engine Reinforcement Learning for LLMs

TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

Official implementation of the paper "Generative Inbetweening through Frame-wise Conditions-Driven Video Generation"

Explorations into adversarial losses on top of autoregressive loss for language modeling

waifu年龄检测器！

An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

A comprehensive codebase for training and finetuning Image <> Latent models.

Pippo: High-Resolution Multi-View Humans from a Single Image

🕷️ Undetectable, Lightning-Fast, and Adaptive Web Scraping for Python

SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

The official implementation of TokenSynth (ICASSP 2025)

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

A low-bitrate single-codebook 16 kHz speech codec based on focal modulation

A collections of audio codecs with a standardized API

[ICASSP 2025] Official implementation of "ViolinDiff: Enhancing Expressive Violin Synthesis with Pitch Bend Conditioning".