Generative models for conditional audio generation

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

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

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Conformer-based Metric GAN for speech enhancement

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

Optimized Stable Diffusion modified to run on lower GPU VRAM

Run upstream VS Code on a remote machine with access through a modern web browser from any device, anywhere.

JAX implementation ViT-VQGAN

CUDA Templates for Linear Algebra Subroutines

InterfaceGAN++: Exploring the limits of InterfaceGAN. In this repository, we propose an approach, termed as InterFaceGAN++, for semantic face editing based on the work from Shen et al. Specifically…

model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution …

🚀 Implementation of easy-to-use 3D parallelism based on Huggingface Transformers & Microsoft DeepSpeed

Contrastive Language-Audio Pretraining

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

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

🐸💬 - Deep learning for Text to Speech by Coqui

Deep learning for Text to Speech

Friendica Communications Platform

Python extension for Visual Studio Code

using world vocoder to extract features and make data for training neural networks

gentle forced aligner

WaveRNN Vocoder + TTS

Pre-trained ELMo Representations for Many Languages

Kaldi extended by Kaituo XU with new features in nnet1.

Multi-speaker Tacotron in TensorFlow.

A deep neural network for finding text-independent speaker embedding written in tensorflow and tensorpack