Metadata-Version: 2.1
Name: waveglow
Version: 22.12.28
Summary: Waveglow library
Home-page: http://github.com/8tm/waveglow
Author: Tadeusz Miszczyk
Author-email: 42252259+8tm@users.noreply.github.com
Requires-Python: >=3.8,<4.0
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Operating System :: Unix
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Requires-Dist: Pillow (>=9.3.0,<10.0.0)
Requires-Dist: Unidecode (>=1.3.6,<2.0.0)
Requires-Dist: inflect (>=6.0.2,<7.0.0)
Requires-Dist: librosa (>=0.9.2,<0.10.0)
Requires-Dist: matplotlib (>=3.6.2,<4.0.0)
Requires-Dist: numpy (>=1.23.5,<2.0.0)
Requires-Dist: scipy (>=1.9.3,<2.0.0)
Requires-Dist: tacotron2 (>=22.12.28,<23.0.0)
Requires-Dist: tensorboardX (>=2.5.1,<3.0.0)
Requires-Dist: tensorflow (>=2.11.0,<3.0.0)
Project-URL: Documentation, https://test.pypi.org/project/waveglow
Project-URL: Repository, http://github.com/8tm/waveglow
Description-Content-Type: text/markdown

# Waveglow library

This Waveglow library was changed to be used with vait library.


## Instalation

### 1) Install waveglow library

(This will also install tacotron2 library)

```shell
pip install waveglow==22.12.28
```


### 2) Install CUDA 11.3 or 11.6

```shell
pip install -r requirements-cuda-11.3.txt
# or
pip install -r requirements-cuda-11.6.txt
```


### 3) Install apex
```shell
git clone https://github.com/NVIDIA/apex /home/${USER}/apex
cd /home/${USER}/apex
pip install -v --disable-pip-version-check --no-cache-dir ./
cd -
```


### 4) Download published model files

```shell
wget https://drive.google.com/open?id=1rpK8CzAAirq9sWZhe9nlfvxMF1dRgFbF
```


### 5) Download mel-spectrograms

```shell
wget https://drive.google.com/file/d/1g_VXK2lpP9J25dQFhQwx7doWl_p20fXA/view?usp=sharing
```


## Usage: Creating audio

```shell
waveglow-inference -f <(ls mel_spectrograms/*.pt) -w waveglow_256channels_universal_v5.pt -o . --is_fp16 -s 0.6
```


## Usage: Training

```shell
mkdir checkpoints
waveglow-train -c config.json
```

