🚀 BigVGAN: A Universal Neural Vocoder with Large-Scale Training
BigVGAN is a universal neural vocoder trained on a large scale. It offers high - quality audio generation capabilities and has various pre - trained models for different scenarios.
Sang - gil Lee, Wei Ping, Boris Ginsburg, Bryan Catanzaro, Sungroh Yoon
[Paper] - [Code] - [[Showcase]](https://bigvgan - demo.github.io/) - [Project Page] - [[Weights]](https://huggingface.co/collections/nvidia/bigvgan - 66959df3d97fd7d98d97dc9a) - [Demo]
[](https://paperswithcode.com/sota/speech - synthesis - on - libritts?p=bigvgan - a - universal - neural - vocoder - with - large)
✨ Features
- Code Refactoring: In July 2024 (v2.3), the code was refactored for better readability.
- CUDA Kernel Optimization: A fully fused CUDA kernel of anti - alised activation was introduced with inference speed benchmark.
- Local Demo: In July 2024 (v2.2), an interactive local demo using gradio was added.
- Hugging Face Integration: In July 2024 (v2.1), BigVGAN was integrated with 🤗 Hugging Face Hub, providing easy access to inference using pretrained checkpoints and an interactive demo on Hugging Face Spaces.
- BigVGAN - v2 Release: In July 2024 (v2), BigVGAN - v2 was released with a custom CUDA kernel for faster inference, an improved discriminator and loss, and trained on larger and more diverse datasets.
📦 Installation
This repository contains pretrained BigVGAN checkpoints with easy access to inference and additional huggingface_hub
support.
If you are interested in training the model and additional functionalities, please visit the official GitHub repository for more information: https://github.com/NVIDIA/BigVGAN
git lfs install
git clone https://huggingface.co/nvidia/bigvgan_v2_44khz_128band_256x
💻 Usage Examples
Basic Usage
Below example describes how you can use BigVGAN: load the pretrained BigVGAN generator from Hugging Face Hub, compute mel spectrogram from input waveform, and generate synthesized waveform using the mel spectrogram as the model's input.
device = 'cuda'
import torch
import bigvgan
import librosa
from meldataset import get_mel_spectrogram
model = bigvgan.BigVGAN.from_pretrained('nvidia/bigvgan_v2_44khz_128band_256x', use_cuda_kernel=False)
model.remove_weight_norm()
model = model.eval().to(device)
wav_path = '/path/to/your/audio.wav'
wav, sr = librosa.load(wav_path, sr=model.h.sampling_rate, mono=True)
wav = torch.FloatTensor(wav).unsqueeze(0)
mel = get_mel_spectrogram(wav, model.h).to(device)
with torch.inference_mode():
wav_gen = model(mel)
wav_gen_float = wav_gen.squeeze(0).cpu()
wav_gen_int16 = (wav_gen_float * 32767.0).numpy().astype('int16')
Advanced Usage
You can apply the fast CUDA inference kernel by using a parameter use_cuda_kernel
when instantiating BigVGAN:
import bigvgan
model = bigvgan.BigVGAN.from_pretrained('nvidia/bigvgan_v2_44khz_128band_256x', use_cuda_kernel=True)
When applied for the first time, it builds the kernel using nvcc
and ninja
. If the build succeeds, the kernel is saved to alias_free_activation/cuda/build
and the model automatically loads the kernel. The codebase has been tested using CUDA 12.1
.
Please make sure that both are installed in your system and nvcc
installed in your system matches the version your PyTorch build is using.
For detail, see the official GitHub repository: https://github.com/NVIDIA/BigVGAN?tab=readme - ov - file#using - custom - cuda - kernel - for - synthesis
📚 Documentation
Pretrained Models
We provide the [pretrained models on Hugging Face Collections](https://huggingface.co/collections/nvidia/bigvgan - 66959df3d97fd7d98d97dc9a).
One can download the checkpoints of the generator weight (named bigvgan_generator.pt
) and its discriminator/optimizer states (named bigvgan_discriminator_optimizer.pt
) within the listed model repositories.
Property |
Details |
Model Name |
bigvgan_v2_44khz_128band_512x, bigvgan_v2_44khz_128band_256x, etc. |
Sampling Rate |
44 kHz, 24 kHz, 22 kHz |
Mel band |
128, 100, 80 |
fmax |
22050, 12000, 11025, 8000 |
Upsampling Ratio |
512, 256 |
Params |
122M, 112M, 14M |
Dataset |
Large - scale Compilation, LibriTTS, LibriTTS + VCTK + LJSpeech |
Steps |
5M |
Fine - Tuned |
No |
📄 License
This project is licensed under the MIT License.