Metadata-Version: 2.1
Name: lvc
Version: 1.0.1
Summary: Unofficial pip package for zero-shot voice conversion
Home-page: https://github.com/fakerybakery/lvc
Author: mrfakename
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: librosa
Requires-Dist: soundfile
Requires-Dist: matplotlib
Requires-Dist: numpy
Requires-Dist: omegaconf
Requires-Dist: praat-parselmouth
Requires-Dist: scipy
Requires-Dist: tensorboard
Requires-Dist: torch
Requires-Dist: torchaudio
Requires-Dist: tqdm
Requires-Dist: transformers
Requires-Dist: cached_path

# LVC

Unofficial pip-installable Python package for [LVC-VC](https://github.com/wonjune-kang/lvc-vc) (zero-shot voice conversion) by Wonjune Kang, Mark Hasegawa-Johnson, Deb Roy.

## Installation

```
pip install lvc
```

## Usage

You can either convert files or convert arrays.

### Convert Files

```python
from lvc import LVC, LVCAudio
l = LVC()

l.infer_file(
    'orig.wav',
    'sample.wav',
    'target.wav',
)
```

### Convert Arrays

```python
from lvc import LVC, LVCAudio
import librosa
import soundfile as sf
l = LVC()

o_y, o_sr = librosa.load('orig.wav')
s_y, s_sr = librosa.load('sample.wav')

o, sr = l.infer_array(
    LVCAudio(o_y, o_sr),
    LVCAudio(s_y, s_sr),
)
sf.write('out.wav', o, sr)
```

## License

MIT
