A beautiful, customizable animated orb component for React applications.

Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

CUDA accelerated rasterization of gaussian splatting

A 3D Gaussian Splatting framework with various derived algorithms and an interactive web viewer

DUSt3R: Geometric 3D Vision Made Easy

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis

A novel graph U-net architecture

Code for "DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training"

MeshGraphNets (MGN)

The official implementation for paper: Improving Knowledge Distillation via Regularizing Feature Norm and Direction

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Collection of audio-focused loss functions in PyTorch

Silero VAD: pre-trained enterprise-grade Voice Activity and Number Detector

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a ca…

An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.

Silero Models: pre-trained STT models and benchmarks made embarrassingly simple

This is the official implementation of the paper AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization.

Python implementation of performance metrics in Loizou's Speech Enhancement book

This repo contains the scripts, models and required files for the Interspeech 2020 Deep Noise Suppression (DNS) Challenge. We are open sourcing clean speech and noise files as well. Participants of…

PESQ (Perceptual Evaluation of Speech Quality) Wrapper for Python Users (narrow band and wide band)

Code for the paper Music Source Separation in the Waveform Domain

Reproducing the Linear Multihead Attention introduced in Linformer paper (Linformer: Self-Attention with Linear Complexity)

Background Matting: The World is Your Green Screen

LogMMSE speech enhancement/noise reduction