Downloads · 30 days
5.2K
14% of all-time downloads
patriotyk/vocos-mel-hifigan-compat-44100khz
vocos-mel-hifigan-compat-44100khz is a audio-to-audio model from patriotyk. Use it for the audio-to-audio task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Vocos is a fast neural vocoder designed to synthesize audio waveforms from acoustic features. Unlike other typical GAN-based vocoders, Vocos does not model audio samples in the time domain. Instead, it generates spect…
Downloads · 30 days
5.2K
14% of all-time downloads
All-time downloads
36.3K
Public
Repo size
1.6 GB
Likes
10
Public
Click a slice to open those files.
.ckpt679 MB · 51%
From the Hugging Face model README
Vocos is a fast neural vocoder designed to synthesize audio waveforms from acoustic features. Unlike other typical GAN-based vocoders, Vocos does not model audio samples in the time domain. Instead, it generates spectral coefficients, facilitating rapid audio reconstruction through inverse Fourier transform.
This version of vocos uses 80-bin mel spectrograms as acoustic features which are widespread in the TTS domain since the introduction of hifi-gan The goal of this model is to provide an alternative to hifi-gan that is faster and compatible with the acoustic output of several TTS models.
The model is aimed to serve as a vocoder to synthesize audio waveforms from mel spectrograms. Is trained to generate speech and if is used in other audio domain is possible that the model won't produce high quality samples.
To use Vocos only in inference mode, install it using:
pip install git+https://github.com/langtech-bsc/vocos.git@matcha
import torch
from vocos import Vocos
vocos = Vocos.from_pretrained("patriotyk/vocos-mel-hifigan-compat-44100khz")
mel = torch.randn(1, 80, 256) # B, C, T
audio = vocos.decode(mel)
The model was trained on private 800+ hours dataset, made from Ukrainian audio books, using narizaka tool.
The model was trained for 2.0M steps and 210 epochs with a batch size of 20. We used a Cosine scheduler with a initial learning rate of 3e-4. We where using two RTX-3090 video cards for training, and it took about one month of continuous training.
Evaluation was done using the metrics on the original repo, after 210 epochs we achieve:
If this code contributes to your research, please cite the work:
@article{siuzdak2023vocos,
title={Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis},
author={Siuzdak, Hubert},
journal={arXiv preprint arXiv:2306.00814},
year={2023}
}