RMSnow's picture
add backend inference and inferface output
0883aa1
raw
history blame
1.7 kB
# This module is from [WeNet](https://github.com/wenet-e2e/wenet).
# ## Citations
# ```bibtex
# @inproceedings{yao2021wenet,
# title={WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit},
# author={Yao, Zhuoyuan and Wu, Di and Wang, Xiong and Zhang, Binbin and Yu, Fan and Yang, Chao and Peng, Zhendong and Chen, Xiaoyu and Xie, Lei and Lei, Xin},
# booktitle={Proc. Interspeech},
# year={2021},
# address={Brno, Czech Republic },
# organization={IEEE}
# }
# @article{zhang2022wenet,
# title={WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit},
# author={Zhang, Binbin and Wu, Di and Peng, Zhendong and Song, Xingchen and Yao, Zhuoyuan and Lv, Hang and Xie, Lei and Yang, Chao and Pan, Fuping and Niu, Jianwei},
# journal={arXiv preprint arXiv:2203.15455},
# year={2022}
# }
#
import torch
class GlobalCMVN(torch.nn.Module):
def __init__(self, mean: torch.Tensor, istd: torch.Tensor, norm_var: bool = True):
"""
Args:
mean (torch.Tensor): mean stats
istd (torch.Tensor): inverse std, std which is 1.0 / std
"""
super().__init__()
assert mean.shape == istd.shape
self.norm_var = norm_var
# The buffer can be accessed from this module using self.mean
self.register_buffer("mean", mean)
self.register_buffer("istd", istd)
def forward(self, x: torch.Tensor):
"""
Args:
x (torch.Tensor): (batch, max_len, feat_dim)
Returns:
(torch.Tensor): normalized feature
"""
x = x - self.mean
if self.norm_var:
x = x * self.istd
return x