keonlee9420/PortaSpeech
PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech
Combines a variational generator with flow-based post-processing to achieve high-quality synthesis at reduced model sizes (7.6M–24M parameters). Implements linguistic encoding via forced alignment with configurable helper losses (DGA/CTC), while supporting speaking rate control and integration with HiFi-GAN or MelGAN vocoders for final audio generation.
341 stars. No commits in the last 6 months.
Stars
341
Forks
38
Language
Python
License
MIT
Category
Last pushed
Feb 17, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/PortaSpeech"
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...