hifigan 开源项目推荐（31 个）

coqui-ai /TTS

一个用于文本转语音的深度学习工具包，已在研究和生产环境中经过实战检验

kan-bayashi /ParallelWaveGAN

带Pytorch的非官方并行WaveGAN（+ MelGAN和多频段MelGAN & HiFi-GAN & StyleMelGAN）

PriesiaMioShirakana /DragonianVoice

多个SVC/TTS的C++推理库

rishikksh20 /hifigan-denoiser

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

karim23657 /Persian-tts-coqui

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

xcmyz /FastVocoder

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

nipponjo /tts-arabic-pytorch

🎙️ Arabic TTS models (Tacotron2, FastPitch)

tuanh123789 /Train_Hifigan_XTTS

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

Rumeysakeskin /Turkish-Text-to-Speech

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

gooofy /zerovox

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

rishikksh20 /iSTFT-Avocodo-pytorch

Ultrafast GAN based Vocoder for Text to Speech

nipponjo /tts_arabic

🎙️ Arabic TTS models (FastPitch, Mixer-TTS) in the ONNX format — Python package for offline speech synthesis 🚀📦

rishikksh20 /multiband-hifigan

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

azraelkuan /repgan

RepVgg + HiFiGAN

Convbased /Convbased-Studio

一个更高质量的 RVC 预训练模型，可加速你的训练过程。

deep-privacy /SA-toolkit

SA-toolkit: Speaker speech anonymization toolkit in python

maxmelichov /blue-codec

Fast and Small codec for flow-matching models

egorsmkv /radtts-hifigan

RADTTS + HiFiGAN vocoder

HoppouAI /ApexSVC

Zero shot singing voice conversion, whats better to make than this on a Monday?

egorsmkv /radtts-uk

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