Metadata-Version: 2.1
Name: voicefixer
Version: 0.0.5
Summary: This package is written for the restoration of degraded speech
Home-page: https://github.com/haoheliu/voicefixer
Author: Haohe Liu
Author-email: haoheliu@gmail.com
License: MIT
Platform: UNKNOWN
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Requires-Python: >=3.7.0
Description-Content-Type: text/markdown
License-File: LICENSE


# VoiceFixer
*Voicefixer* aims at the restoration of human speech regardless how serious its degraded. It can handle noise, reveberation, low resolution (2kHz~44.1kHz) and clipping (0.1-1.0 threshold) effect within one model.

![idea](pics/idea.png)
![idea](pics/pipline.png)

## Usage
```python
from voicefixer import VoiceFixer
voicefixer = VoiceFixer()
voicefixer.restore(input="", # input wav file path
                   output="", # output wav file path
                   cuda=False, # whether to use gpu acceleration
                   mode = 0) # You can try out mode 0, 1, 2 to find out the best result


from voicefixer import Vocoder
# Universal Speaker Independent Vocoder
vocoder = Vocoder(sample_rate=44100) # only support 44100 sample rate
vocoder.oracle(fpath="", # input wav file path
               out_path="") # output wav file path
```



![idea](pics/real_demos/tiedaoyoujidui.png)
![idea](pics/real_demos/xigua.png)















