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
Usage
from hifigan_vocoder import hifigan, get_sample_mel
mel = get_sample_mel(dataset='uni', device='cpu') # dataset in ['uni', 'vctk']
print(mel.shape) # torch.Size([1, 80, 2062])
model = hifigan()
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-0.0.1.tar.gz
(565.1 kB
view hashes)
Built Distribution
Close
Hashes for hifigan_vocoder-0.0.1-py3-none-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b02d23c3524e0b60db79031bd8326716b07dd5cc76a7b4f1f2eecdfdf1e22f88 |
|
MD5 | 7a640c6034096dfa3d4d2c0470e783fd |
|
BLAKE2b-256 | b01811489790af2e3be07dd23356776d248ce1672b5956f90337948f4eaec79a |