README.md

metadata

datasets:
  - mesolitica/Malaysian-Emilia
language:
  - ms
  - en
base_model:
  - charactr/vocos-mel-24khz

Malaysian Vocos

Continue pretraining charactr/vocos-mel-24khz on Malaysian Emilia to make it more crispy for Malaysian context!

Installation

To use Vocos only in inference mode, install it using:

pip install vocos

Usage

Reconstruct audio from mel-spectrogram

import torch

from vocos import Vocos

vocos = Vocos.from_pretrained("mesolitica/malaysian-vocos-mel-24khz")

mel = torch.randn(1, 100, 256)  # B, C, T
audio = vocos.decode(mel)