kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
This project helps developers working on advanced speech synthesis to create natural-sounding spoken audio and even singing voices in real-time. It takes linguistic features or acoustic representations (like Mel spectrograms) and converts them into high-quality raw audio waveforms. The ideal user is a machine learning engineer or researcher focused on building custom text-to-speech (TTS) or singing voice synthesis (SVS) systems.
1,637 stars. No commits in the last 6 months.
Use this if you need to integrate a state-of-the-art neural vocoder into a text-to-speech or singing voice synthesis system that requires high-quality, real-time audio output.
Not ideal if you are looking for a ready-to-use application to convert text to speech without any coding or model integration.
Stars
1,637
Forks
352
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kan-bayashi/ParallelWaveGAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
fatchord/WaveRNN
WaveRNN Vocoder + TTS
shangeth/wavencoder
WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation,...
rishikksh20/iSTFTNet-pytorch
iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier...
seungwonpark/melgan
MelGAN vocoder (compatible with NVIDIA/tacotron2)
lucasnewman/best-rq-pytorch
Implementation of BEST-RQ - a model for self-supervised learning of speech signals using a...