Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Enable Opencode to authenticate against Antigravity (Google's IDE) via OAuth so you can use Antigravity rate limits and access models like gemini-3-pro and claude-opus-4-5-thinking with your Google…

Neural network 3D visualization framework, build interactive and intuitive model in browsers, support pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js

The official implementation of HierSpeech++

The official implementation of GTCRN, an ultra-lightweight SE model.

Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

AI-based Audio Watermarking Tool

Instant voice cloning by MIT and MyShell. Audio foundation model.

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Efficient neural speech synthesis

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

Modern audio compression for the internet.

A markdown version emoji cheat sheet

Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics (ECCV2024)

[CVPR 2023] Unofficial PyTorch implementation for CVPR2023 paper, Prototypical Residual Networks for Anomaly Detection and Localization.

Diffusion-based singing voice pitch correction

GANs with spectral normalization and projection discriminator

This is an official PyTorch implementation for "MuSc : Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images" (MuSc ICLR2024).

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Audio samples from "HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis"

Code for Transformers Solve Limited Receptive Field for Monocular Depth Prediction

Pytorch Implementation of "Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation" paper on cityscapes dataset

This is an unofficial implementation of Reconstruction by inpainting for visual anomaly detection (RIAD).

Keras documentation, hosted live at keras.io

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

AI Wiki

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations