HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
-
Updated
Mar 2, 2021 - Python
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Include Basis-MelGAN, MelGAN, HifiGAN and Multiband-HifiGAN, maybe NHV in the future.
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
Ultrafast GAN based Vocoder for Text to Speech
RADTTS + HiFiGAN vocoder
Speech synthesis (TTS) in low-resource languages by training from scratch with Fastpitch and fine-tuning with HifiGan
SA-toolkit: Speaker speech anonymization toolkit in python
TTS for Arabic (FastPitch) in the ONNX format
StreamHiFiGAN offers a HiFiGAN vocoder model optimized for streaming inference, providing real-time audio synthesis capabilities.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Add a description, image, and links to the hifigan topic page so that developers can more easily learn about it.
To associate your repository with the hifigan topic, visit your repo's landing page and select "manage topics."