npuichigo/waveglow
A PyTorch implementation of the WaveGlow: A Flow-based Generative Network for Speech Synthesis
Implements invertible coupling layers with glow-based architecture to enable parallel waveform generation conditioned on mel-spectrogram features extracted via Tacotron-compatible pipelines. Supports both training on datasets like CMU Arctic and inference-time synthesis through local conditioning, allowing integration with existing text-to-speech frontends that produce acoustic features.
205 stars. No commits in the last 6 months.
Stars
205
Forks
35
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 06, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/npuichigo/waveglow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shangeth/wavencoder
WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation,...
fatchord/WaveRNN
WaveRNN Vocoder + TTS
kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
seungwonpark/melgan
MelGAN vocoder (compatible with NVIDIA/tacotron2)
rishikksh20/iSTFTNet-pytorch
iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier...