# NVIDIA/BigVGAN

Official PyTorch implementation of BigVGAN (ICLR 2023)

Repository: https://github.com/NVIDIA/BigVGAN
Canonical: https://ross.abutalabs.com/products/bigvgan
Homepage: https://bigvgan-demo.github.io/
Language: Python
License: MIT
License Family: permissive
Topics: audio-synthesis, speech-synthesis, music-synthesis, neural-vocoder, audio-generation, singing-voice-synthesis
Last push: 2024-09-05T03:50:02+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1548, "days_push": 727, "days_rel": 727, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1227, forks 147 (observed 2026-08-28T04:04:03.266413+00:00)

## What it is
BigVGAN is NVIDIA's official PyTorch implementation of a universal neural vocoder (ICLR 2023) that generates high-fidelity raw audio waveforms from acoustic features using large-scale GAN training. It includes pretrained checkpoints up to 44 kHz, custom fused CUDA kernels for fast inference, and Hugging Face Hub integration.

## Use cases
- convert mel spectrograms to audio waveforms with a neural vocoder
- synthesize high-quality speech audio for TTS pipelines
- generate singing voice and instrumental audio from acoustic features
- run zero-shot vocoding on unseen speakers, languages, and recording conditions
- accelerate vocoder inference with fused CUDA kernels on GPU
- fine-tune or train a GAN-based vocoder on custom audio datasets

## When to choose
- you need a state-of-the-art universal vocoder that generalizes out-of-distribution without fine-tuning
- you want pretrained checkpoints supporting up to 44 kHz audio and 512x upsampling
- you need fast GPU inference with optimized CUDA kernels
- you want easy integration via Hugging Face Hub

## When to avoid
- you need CPU-only inference at scale, since it is optimized for NVIDIA GPUs
- you need a full end-to-end text-to-speech system rather than a vocoder component
- you require non-PyTorch frameworks like TensorFlow or JAX

## Facets
- artifact type: library
- maturity: stable
- function: audio-processing, machine-learning, deep-learning, tts
- domain: speech-processing, machine-learning, deep-learning
- platform: python, cross-platform
- tags: neural-vocoder, gan, speech-synthesis, audio-generation, pytorch, cuda-kernel, pretrained-models, hugging-face, audio, gpu, linux

## Member repositories
- NVIDIA/BigVGAN (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:03.266413+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:13.703807+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/BigVGAN (fetched 2026-08-28T04:04:03.266413+00:00, sha 28a48f79be2c)
  - homepage: https://bigvgan-demo.github.io/ (fetched 2026-08-29T12:23:13.123025+00:00, sha cb33bdff3101)
- Data as of 2026-08-30T08:39:29.467469+00:00.