diver-j/melgan-multi
MelGAN Multi GPU Implementation.
This project helps audio engineers and researchers generate realistic human speech from text using deep learning. It takes the LJSpeech dataset of audio recordings and their corresponding text, then processes them to train a model that can synthesize new speech. The primary users are individuals working on text-to-speech systems or speech synthesis research.
No commits in the last 6 months.
Use this if you need to train a high-quality speech synthesis model using generative adversarial networks, especially if you have access to multiple GPUs for faster training.
Not ideal if you're looking for a ready-to-use speech synthesis tool for immediate audio generation without training, or if you don't have access to NVIDIA GPUs and CUDA.
Stars
8
Forks
1
Language
Python
License
—
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/diver-j/melgan-multi"
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)