🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

vits2 backbone with multilingual-bert

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

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

General Speech Restoration

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

PyTorch Implementation of FastDiff (IJCAI'22)

VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network

A fast, high-quality neural vocoder.

Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)

iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier Transform

Vietnamese Text to Speech library

ICASSP 2023 Accepted

Official repository for the paper "Chunked Autoregressive GAN for Conditional Waveform Synthesis"

A toolkit for non-parallel voice conversion based on vector-quantized variational autoencoder

Official Implement of Multi-Stage Multi-Codebook (MSMC) TTS

Include Basis-MelGAN, MelGAN, HifiGAN and Multiband-HifiGAN, maybe NHV in the future.

Official implementation of "Avocodo: Generative Adversarial Network for Artifact-Free Vocoder" (AAAI2023)