rishikksh20/iSTFTNet-pytorch
iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier Transform
This project helps audio engineers and researchers quickly convert mel-spectrograms into high-quality audio waveforms. You provide the mel-spectrogram, and it generates the corresponding sound. It's designed for individuals working on speech synthesis or audio generation who need a fast and efficient way to create audio from spectral representations.
274 stars. No commits in the last 6 months.
Use this if you need a speedy way to turn mel-spectrograms into audible speech or other sound, especially if you prioritize fast processing and smaller model size.
Not ideal if you need a production-ready, highly optimized solution, as this repository is primarily for testing and experimentation.
Stars
274
Forks
49
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rishikksh20/iSTFTNet-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,...
seungwonpark/melgan
MelGAN vocoder (compatible with NVIDIA/tacotron2)
lucasnewman/best-rq-pytorch
Implementation of BEST-RQ - a model for self-supervised learning of speech signals using a...