A wrapped hifi-gan vocoder for easy use.
Project description
hifigan
A wrapped hifi-gan vocoder for easy use.
Source: https://github.com/jik876/hifi-gan
Install
pip install hifigan-vocoder
Usage
from hifigan_vocoder import hifigan, get_sample_mel
mel = get_sample_mel()
print(mel.shape) # torch.Size([1, 80, 2062])
model = hifigan(dataset='uni', device='cpu') # dataset in ['uni', 'vctk']; device in ['cpu', 'cuda']; checkpoint will be downloaded from google driver.
audio = model.infer(mel)
print(mel.shape) # (527872,)
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
hifigan-vocoder-0.1.1.tar.gz
(565.4 kB
view hashes)
Built Distribution
Close
Hashes for hifigan_vocoder-0.1.1-py3-none-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e837d0e9b7ff634a701af85b09d54e43a84d7f077dc556311191f3cdfc1bca4b |
|
MD5 | 8e4992962fe45b90681c79eb55ca9803 |
|
BLAKE2b-256 | b85ceac8761488bc04a12f61a939ff51b86b8faa55c5bf03684de5373adc3f7d |