https://github.com/voidful/audio-preprocessing-pipeline
https://github.com/voidful/audio-preprocessing-pipeline
Last synced: 4 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/voidful/audio-preprocessing-pipeline
- Owner: voidful
- License: mit
- Created: 2022-09-22T16:08:27.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2022-10-06T15:50:10.000Z (over 3 years ago)
- Last Synced: 2025-09-04T02:43:43.556Z (10 months ago)
- Language: Python
- Size: 20.5 KB
- Stars: 3
- Watchers: 3
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# audio-preprocessing-pipeline
## Preparation
```shell
apt-get install libsox-fmt-all libsox-dev sox
add-apt-repository -y ppa:savoury1/ffmpeg4
apt-get -qq install -y ffmpeg
```
## Usage
### Convert audio format to ogg and sampling to 16k
`python convert_format_sampling.py -s /audio_folder/ -w 30`
### Language Identification (LID) and speech enhancement
```python
from lid_enhancement import AudioLIDEnhancer
ase = AudioLIDEnhancer(enable_enhancement=False)
print(ase('test.ogg'))
```
## References
Denoiser copied
from [fairseq](https://github.com/facebookresearch/fairseq/tree/main/examples/speech_synthesis/preprocessing/denoiser)