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

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

多个SVC/TTS的C++推理库

HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

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

Persian/Farsi text to speech(TTS) training using coqui tts

TTS models for Arabic (Tacotron2, FastPitch)

This is an implementation for train hifigan part of XTTSv2 model using Coqui/TTS.

Ultrafast GAN based Vocoder for Text to Speech

Speech synthesis (TTS) in low-resource languages by training from scratch with Fastpitch and fine-tuning with HifiGan

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

RepVgg + HiFiGAN

zero-shot realtime TTS system, fully offline, free and open source

SA-toolkit: Speaker speech anonymization toolkit in python

RADTTS + HiFiGAN vocoder

TTS for Arabic (FastPitch) in the ONNX format

🇺🇦 Ukrainian RAD-TTS++ models (decoder + models with 3 voices) and HiFiGAN model

homework for deep generation. Combine FastSpeech2 with different vocoders ⭐REFERENCE (modify origin repos): https://github.com/ming024/FastSpeech2 https://github.com/NVIDIA/waveglow https://github.com/mindslab-ai/univnet https://github.com/jik876/hifi-gan

Training and Tunning a Text to speech model with Nvidia NeMo and Weights and Biases