Malaysian Vocos
Pretrained charactr/vocos-mel-24khz from scratch on Malaysian Emilia to make it more crispy for Malaysian context!
- We increase number of layers.
- We increase hidden layer size.
Wandb at https://wandb.ai/huseinzol05/malaysian_vocos_mel_v2?nw=nwuserhuseinzol05, still on training
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)
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.