diggerdu/pytorch_audio
audio processing module for pytorch:stft, istft
This module helps you analyze and recreate audio signals by converting them between their sound wave form and their frequency components. It takes an audio signal as input and can output its frequency spectrum, or take frequency information and output a reconstructed audio signal. Audio engineers, researchers working with sound, or machine learning practitioners building audio applications would find this useful.
No commits in the last 6 months.
Use this if you need to break down audio into its constituent frequencies for analysis or to reconstruct audio from frequency data within a PyTorch workflow.
Not ideal if you need a full-featured audio editing suite or advanced signal processing capabilities beyond core time-frequency transformations.
Stars
36
Forks
7
Language
Python
License
—
Category
Last pushed
Aug 15, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/diggerdu/pytorch_audio"
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)