https://github.com/egorsmkv/radtts-hifigan
RADTTS + HiFiGAN vocoder
https://github.com/egorsmkv/radtts-hifigan
conversational-ai hifigan speech-synthesis text-to-speech tts ukrainian vocoder
Last synced: 3 months ago
JSON representation
RADTTS + HiFiGAN vocoder
- Host: GitHub
- URL: https://github.com/egorsmkv/radtts-hifigan
- Owner: egorsmkv
- Created: 2023-01-01T21:34:46.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-04-07T13:45:32.000Z (over 2 years ago)
- Last Synced: 2025-04-20T00:51:42.435Z (8 months ago)
- Topics: conversational-ai, hifigan, speech-synthesis, text-to-speech, tts, ukrainian, vocoder
- Language: Python
- Homepage:
- Size: 62.5 KB
- Stars: 9
- Watchers: 2
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: licenses/RADTTS-LICENSE
Awesome Lists containing this project
README
# RADTTS + HiFiGAN vocoder
🇺🇦 Join Ukrainian Text-to-Speech community: https://t.me/speech_synthesis_uk
---
Clone the code:
```bash
git clone https://github.com/egorsmkv/radtts-hifigan
cd radtts-hifigan
```
Install dependencies:
```bash
pip install -r requirements.txt
```
Download Ukrainian RADTTS and HiFiGAN models:
```bash
mkdir models
cd models
wget https://github.com/egorsmkv/radtts-hifigan/releases/download/v1.0/hifi_config.json
wget https://github.com/egorsmkv/radtts-hifigan/releases/download/v1.0/hifi_vocoder.pt
wget https://github.com/egorsmkv/radtts-istftnet/releases/download/v1.0/RADTTS-Lada.pt
```
Then you can inference own texts by the following command:
```bash
python3 inference.py -c config_ljs_dap.json -r models/RADTTS-Lada.pt -t test_sentences.txt --vocoder_path models/hifi_vocoder.pt --vocoder_config_path models/hifi_config.json -o results/
```