mirror of
https://github.com/wassname/TTS.git
synced 2026-10-30 13:00:27 +08:00
manmay nakhashi
bc422f2f3c
* added EnergyDataset * add energy to Dataset * add comupte_energy * added energy params * added energy to forward_tts * added plot_avg_energy for visualisation * Update forward_tts.py * create file * added fastspeech2 recipe * add fastspeech2 config * removed energy from fast pitch * add energy loss to forward tts * Update fastspeech2_config.py * change run_name * Update numpy_transforms.py * fix typo * fix typo * fix typo * linting issues * use_energy default value --> False * Update numpy_transforms.py * linting fixes * fix typo * liniting_fix * liniting_fix * fix * fixes * fixes * lint fix * lint fixws * added training test * wrong import * wrong import * trailing whitespace * style fix * changed class name because of error * class name change * class name change * change class name * fixed styles
🐸💬 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.pyRunning 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 💪.