Convert any PDF into a podcast episode!

A Chrome 🌐 & Firefox 🦊 extension to discover the latest developer news and tools in one tab!

The personal, minimalist, super-fast, database free, bookmarking service - community repo

Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles.

Incredibly fast Whisper-large-v3

*CREPE+HYBRID TRAINING* A very experimental fork of the Retrieval-based-Voice-Conversion-WebUI repo that incorporates a variety of other f0 methods, along with a hybrid f0 nanmedian method.

VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

Fast TorToiSe inference (5x or your money back!)

Instruct-tune LLaMA on consumer hardware

A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick

Fork of Facebooks LLaMa model to run on CPU

Quantized inference code for LLaMA models

无需情感标注的情感可控原神+崩三全人物语音合成模型，基于VITS

Optimized Stable Diffusion modified to run on lower GPU VRAM

A variant on ashawkey/stable-dreamfusion, operating in latent space

stable diffusion finetuned on weeb stuff

Diffusers Stable Diffusion as a Cog model

Retrieval augmented diffusion from CompVis.

Convert .py files runnable in VSCode/Python or Atom/Hydrogen to jupyter/colab .ipynb notebooks and vice versa

StyleGAN Encoder - converts real images to latent space

StyleGAN Encoder - converts real images to latent space

Webcam demo for SKTBrain/DiscoGAN

Efficient neural speech synthesis

Pytorch implementation of Deepmind's WaveRNN model

Instagram filters hacked and open sourced. Supports both photo and video.

Speech-conditioned face generation using Generative Adversarial Networks (ICASSP 2019)

Deepmind's Tacotron-2 Tensorflow implementation