A PyPI port of the NVIDIA Tacotron2 model
Project description
tacotron2-model
A PyPI port of the NVIDIA Tacotron2 model
Source: https://github.com/NVIDIA/tacotron2 (model.py)
A pytorch install is required but is not added to requirements to avoid configuration issues.
The only change from the NVIDIA original is a replacement of hparams with individual arguments. This removes the dependency on tf.contrib.training.HParams (deprecated since tensorflow 1).
Model usage
from tacotron2_model import Tacotron2
symbols = "!\'(),.:;?_- ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
model = Tacotron2(n_symbols=len(symbols)).cuda()
print(model.eval())
Loss usage
from tacotron2_model import Tacotron2Loss
criterion = Tacotron2Loss()
Collate usage
from tacotron2_model import TextMelCollate
collate_fn = TextMelCollate()
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tacotron2-model-0.1.11.tar.gz
(10.9 kB
view hashes)
Built Distribution
Close
Hashes for tacotron2_model-0.1.11-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f33999b6ec75019c5e85c93dd00e1764fac49a7191ecbd8d282e4f2439136c12 |
|
MD5 | 517fb87c7a9c5d5588118884f181f565 |
|
BLAKE2b-256 | 1c512fbea863188a838c84f46c5608a51b54b01b399a773e516de26532ad9810 |