PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

Wan: Open and Advanced Large-Scale Video Generative Models

This repository contains the code for the paper "voc2vec: A Foundation Model for Non-Verbal Vocalization", accepted at ICASSP 2025.

Genome modeling and design across all domains of life

The official implementation of TokenSynth (ICASSP 2025)

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

s1: Simple test-time scaling

Fully open reproduction of DeepSeek-R1

Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

Training Large Language Model to Reason in a Continuous Latent Space

Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.

Code for the paper "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"

[INTERSPEECH 2024] EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark

A parallel ODE solver for PyTorch

The best OSS video generation models

Fourier Dual Diffusion

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Out-of-the-box (OOTB) GUI Agent for Windows and macOS

Awesome speech/audio LLMs, representation learning, and codec models

Awesome speech/audio LLMs, representation learning, and codec models

Speaker change detection using SincNet and an LSTM/Transformer

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.