This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor

无需情感标注的情感可控语音合成模型，基于VITS

Best TTS based on BERT and VITS with some Natural Speech Features Of Microsoft

A fully working pytorch implementation of NaturalSpeech (Tan et al., 2022)

Open source voice labeling application

Port of OpenAI's Whisper model in C/C++

Deezer source separation library including pretrained models.

Deep learning for audio denoising

A Python/Pytorch app for easily synthesising human voices

Objective metrics used in several text-to-speech (TTS) papers.

Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

DeepMind's Tacotron-2 Tensorflow implementation

Getting Started with Xilinx ML Suite

Computation using data flow graphs for scalable machine learning

Code accompanying blog posts about doc2vec