Downloads · 30 days
62
16% of all-time downloads
wetdog/vocos-mel-24khz-onnx
vocos-mel-24khz-onnx is a machine learning model from wetdog. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
Downloads · 30 days
62
16% of all-time downloads
All-time downloads
400
Public
Repo size
54.2 MB
Likes
2
Public
Click a slice to open those files.
.onnx54.2 MB · 100%
From the Hugging Face model README
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
Audio samples | Paper [abs] [pdf]
Vocos is a fast neural vocoder designed to synthesize audio waveforms from acoustic features. Trained using a Generative Adversarial Network (GAN) objective, Vocos can generate waveforms in a single forward pass. 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 is a ONNX version of the original 24khz mel spectrogram model. The model predicts spectrograms and the ISTFT is performed outside ONNX as ISTFT is still not implemented as an operator in ONNX.
Try out in colab:
<a target="_blank" href="https://colab.research.google.com/drive/1J1tWd56D7CPwmVCP-pbMNzlRWYvlyADN"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a>@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}
}