git clone https://github.com/ryota-komatsu/speaker_disentangled_hubert.git
cd speaker_disentangled_hubert

sudo apt install git-lfs  # for UTMOS

conda create -y -n py310 -c pytorch -c nvidia -c conda-forge python=3.10.19 pip=24.0 faiss-gpu=1.12.0
conda activate py310
pip install -r requirements/requirements.txt

sh scripts/setup.sh

python

import torchaudio

from src.bigvgan.bigvgan import BigVGan
from src.bigvgan.data import mel_spectrogram

wav_path = "/path/to/wav"

model = BigVGan.from_pretrained("ryota-komatsu/bigvgan", device_map="cuda")

# load a waveform
waveform, sr = torchaudio.load(wav_path)
waveform = torchaudio.functional.resample(waveform, sr, 16000)
waveform = waveform.cuda()

spectrogram = mel_spectrogram(waveform)
spectrogram = spectrogram.transpose(1, 2)

audio_values = model(spectrogram)

Training Details

Training Data

16 kHz-downsampled LibriTTS-R train set

Training Hyperparameters

Training regime: bf16 mixed precision

Model Architecture

BigVGAN-v2