rishikksh20/Fre-GAN-pytorch
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis
This tool helps researchers and audio engineers synthesize high-quality audio from various input parameters, ensuring the generated sound maintains consistent frequency characteristics. It takes in acoustic features, often derived from speech or other audio, and produces realistic, natural-sounding audio waveforms. This is ideal for those working on advanced audio generation tasks.
111 stars. No commits in the last 6 months.
Use this if you need to generate very high-fidelity, natural-sounding audio that precisely matches the frequency characteristics of your input acoustic features.
Not ideal if you're looking for a complete, end-to-end voice cloning or text-to-speech solution, as this focuses specifically on the audio synthesis (vocoder) component.
Stars
111
Forks
31
Language
Python
License
MIT
Category
Last pushed
Aug 26, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rishikksh20/Fre-GAN-pytorch"
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)