History

Eren Gölge 37959ad0c7 Make linter		2021-09-30 23:02:16 +00:00
..
align_tts	Update `align_tts` for trainer_v2	2021-09-30 14:18:10 +00:00
fast_pitch	Update ForwardTTS for Trainer_v2	2021-09-30 14:19:19 +00:00
fast_speech	Update ForwardTTS for Trainer_v2	2021-09-30 14:19:19 +00:00
glow_tts	Update GlowTTS	2021-09-30 14:47:56 +00:00
hifigan	Update GAN for Trainer_v2	2021-09-30 14:47:56 +00:00
multiband_melgan	Update GAN for Trainer_v2	2021-09-30 14:47:56 +00:00
speedy_speech	Make linter	2021-09-30 23:02:16 +00:00
tacotron2-DCA	Remove old Tacotron recipes	2021-09-30 14:47:56 +00:00
tacotron2-DDC	Remove old Tacotron recipes	2021-09-30 14:47:56 +00:00
univnet	Fix imports	2021-09-30 14:47:56 +00:00
vits_tts	Fix imports	2021-09-30 14:47:56 +00:00
wavegrad	Fix imports	2021-09-30 14:47:56 +00:00
wavernn	Fix imports	2021-09-30 14:47:56 +00:00
README.md	Create LJSpeech recipes for all the models	2021-06-22 16:21:11 +02:00
download_ljspeech.sh	Create LJSpeech recipes for all the models	2021-06-22 16:21:11 +02:00

README.md

🐸💬 TTS LJspeech Recipes

For running the recipes

Download the LJSpeech dataset here either manually from its official website or using download_ljspeech.sh.
Go to your desired model folder and run the training.

Running Python files. (Choose the desired GPU ID for your run and set CUDA_VISIBLE_DEVICES)
```
CUDA_VISIBLE_DEVICES="0" python train_modelX.py
```
Running bash scripts.
```
bash run.sh
```

💡 Note that these runs are just templates to help you start training your first model. They are not optimized for the best result. Double-check the configurations and feel free to share your experiments to find better parameters together 💪.