Stars
12 Weeks, 24 Lessons, AI for All!
🔊 Text-Prompted Generative Audio Model
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
This repository contains the source code for the paper First Order Motion Model for Image Animation
This repository contains implementations and illustrative code to accompany DeepMind publications
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
A unified framework for 3D content generation.
Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
MARS5 speech model (TTS) from CAMB.AI
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data
This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.
Convert human motion from video to .bvh
A working example of RAG using LLama 2 70b and Llama Index
Deep learning codes and projects using Python
Automatic Music Transcription with Deep Neural Networks
Hands On Natural Language Processing with Python, published by Packt
TensorFlow Lite models for MIRNet for low-light image enhancement.
A deep learning model to lip-sync a given video with any given audio. It uses GAN architecture to orchestrate loss reconstruction or training.
Open source marketing mix modeling code for vexpower.com
Single Pass Spectrogram Inversion in a Jupyter Python notebook
How to run Keras model inference x3 times faster with CPU and Intel OpenVINO
Model Pruning and Quantization using Tensorflow