Rongjiehuang/Multiband-WaveRNN
An unofficial implement of autoregressive vocoder Multiband-WaveRNN. Audio samples in https://rongjiehuang.github.io/Multiband-WaveRNN/
This project helps developers and researchers working on speech synthesis to generate high-quality audio from speech models. You provide an existing dataset of spoken audio, and it generates synthetic speech samples. It's intended for those who need to experiment with and implement autoregressive vocoder models.
No commits in the last 6 months.
Use this if you are a developer or researcher looking to implement and train an autoregressive vocoder model for speech generation.
Not ideal if you need a user-friendly, out-of-the-box solution for text-to-speech without coding or model training.
Stars
28
Forks
5
Language
Python
License
MIT
Category
Last pushed
Feb 12, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Rongjiehuang/Multiband-WaveRNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
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)