https://github.com/khaykingleb/hifi-gan

Vocoder for TTS
https://github.com/khaykingleb/hifi-gan

gan hifi-gan pytorch tts vocoder

Last synced: 2 months ago
JSON representation

Vocoder for TTS

• Host: GitHub
• URL: https://github.com/khaykingleb/hifi-gan
• Owner: khaykingleb
• License: mit
• Created: 2021-12-15T10:59:16.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2021-12-25T14:48:28.000Z (over 4 years ago)
• Last Synced: 2025-03-29T20:44:45.941Z (over 1 year ago)
• Topics: gan, hifi-gan, pytorch, tts, vocoder
• Language: Python
• Homepage:
• Size: 28.5 MB
• Stars: 1
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Neural-Vocoder

## Model

[HiFi-GAN](https://arxiv.org/pdf/2010.05646.pdf) Implementation for TTS.

### Generator 



    



### Discriminator 



    



## Notebook

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/khaykingleb/Neural-Vocoder/blob/main/notebooks/notebook.ipynb)

## Getting Started

Clone the repository and step into it:

```shell

git clone https://github.com/khaykingleb/Text-to-Speech.git

cd Text-to-Speech

```

Install requirements and modules.

```shell

pip install -r requirements.txt

python setup.py install

```

Use for training:

```shell

python main.py -c configs/cofig_name.json

```