Metadata-Version: 2.1
Name: torchlibrosa
Version: 0.0.2
Summary: PyTorch implemention of part of librosa functions.
Home-page: https://github.com/qiuqiangkong/torchlibrosa
Author: Qiuqiang Kong
Author-email: qiuqiangkong@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown

# Pytorch implementation of Fourier transform of librosa library. 

This codebase implemented discrete Fourier Transform (DFT), inverse DFT as neural network layers in pytorch and can be calculated on GPU. Users can extract log mel spectrogram on GPU. The results are the same as obtained using librosa. The code is developed using pytorch 1.0. 

# Usage
Running examples:
```
python stft.py
```


# Summary
This code provides Fourier transform related functions which can be calculated on GPU using pytorch. 


