End-to-End Speech Processing Toolkit

An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.

A tensorflow implementation of the "Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis"

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

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

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)

Neural Style and MSG-Net

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

DeepMind's Tacotron-2 Tensorflow implementation

DeepMind's Tacotron-2 Tensorflow implementation

html5 js 录音 mp3 wav ogg webm amr g711a g711u 格式，支持pc和Android、iOS部分浏览器、Hybrid App（提供Android iOS App源码）、微信，提供ASR语音识别转文字 H5版语音通话聊天示例 DTMF编码解码

（已过时）中文语音合成，改自 https://github.com/Rayhane-mamah/Tacotron-2 和 https://github.com/begeekmyfriend/Tacotron-2