Home/Inference & Serving/ParallelWaveGAN
ParallelWaveGAN logo

ParallelWaveGAN

kan-bayashi/ParallelWaveGAN

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

GraphCanon updated 3w · GitHub synced 3w · 28 views this month

1.6k stars352 forksLast push 2y Jupyter Notebook MIT

Decision brief

ParallelWaveGAN synthesizes speech from mel-spectrograms using PyTorch-based GANs with support for distributed multi-GPU training.

Good fit when

  • When needing to generate natural speech from mel-spectrogram inputs, especially in environments requiring scalable GPU computing.
  • For applications where high-quality speech synthesis aligning closely with input spectrogram patterns is critical.

Avoid when

  • If you're working without access to a PyTorch-compatible GPU setup or need real-time processing capabilities not supported here.
  • In scenarios preferring tools that don't require specific Python and library versions for compatibility.

Observed Jul 12, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Dormant (828d since push)
As of 3w
Provenance
Not a fork · Personal account
As of 3w
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/kan-bayashi/ParallelWaveGAN

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A repository for generating realistic speech from mel-spectrograms using various PyTorch-based generative adversarial networks.

Capability facts

Languages
jupyter notebook

Source: github.language · Jul 29, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 29, 2026)

- Python 3.8+
Source link

Tags

README

Requirements

This repository is tested on Ubuntu 20.04 with a GPU Titan V.

  • Python 3.8+
  • Cuda 11.0+
  • CuDNN 8+
  • NCCL 2+ (for distributed multi-gpu training)
  • libsndfile (you can install via sudo apt install libsndfile-dev in ubuntu)
  • jq (you can install via sudo apt install jq in ubuntu)
  • sox (you can install via sudo apt install sox in ubuntu)

Different cuda version should be working but not explicitly tested.
All of the codes are tested on Pytorch 1.8.1, 1.9, 1.10.2, 1.11.0, 1.12.1, 1.13.1, 2.0.1 and 2.1.0.


If you want to use distributed training, please install


command to install apex.

$ make apex


Note that we specify cuda version used to compile pytorch wheel.  
If you want to use different cuda version, please check `tools/Makefile` to change the pytorch wheel to be installed.

---

# If not, please install via pip
$ pip install parallel_wavegan

---

# Please install this repository in ESPnet conda (or virtualenv) environment
$ . ./path.sh && pip install -U parallel_wavegan

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.