NTT123/hifigan-tpu
Train HiFi-GAN on TPU
This project helps machine learning engineers and researchers accelerate their work in speech synthesis. It allows you to train HiFi-GAN, a high-quality audio generation model, using Google TPUs. You provide audio data and it outputs a trained model capable of generating realistic speech.
No commits in the last 6 months.
Use this if you need to train HiFi-GAN vocoders faster and more efficiently, especially with access to Google TPUs.
Not ideal if you are looking for a pre-trained model or a tool that doesn't require direct interaction with model training scripts.
Stars
10
Forks
—
Language
Python
License
MIT
Category
Last pushed
Apr 03, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/NTT123/hifigan-tpu"
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)