rishikksh20/VocGAN
VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network
This tool helps researchers and developers in speech synthesis convert audio features, specifically mel spectrograms, back into high-fidelity, real-time audio. It takes processed audio features as input and outputs natural-sounding speech. This is ideal for those creating or experimenting with text-to-speech systems or voice cloning.
321 stars. No commits in the last 6 months.
Use this if you need to quickly generate high-quality speech audio from mel spectrograms for your speech synthesis projects.
Not ideal if you're looking for a complete, end-to-end text-to-speech system that handles both text processing and audio generation.
Stars
321
Forks
59
Language
Python
License
MIT
Category
Last pushed
Jul 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rishikksh20/VocGAN"
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)