mirror of
https://github.com/wassname/TTS.git
synced 2026-09-25 13:20:28 +08:00
Shivam Mehta
3b8b105b0d
* Adding encoder * currently modifying hmm * Adding hmm * Adding overflow * Adding overflow setting up flat start * Removing runs * adding normalization parameters * Fixing models on same device * Training overflow and plotting evaluations * Adding inference * At the end of epoch the test sentences are coming on cpu instead of gpu * Adding figures from model during training to monitor * reverting tacotron2 training recipe * fixing inference on gpu for test sentences on config * moving helpers and texts within overflows source code * renaming to overflow * moving loss to the model file * Fixing the rename * Model training but not plotting the test config sentences's audios * Formatting logs * Changing model name to camelcase * Fixing test log * Fixing plotting bug * Adding some tests * Adding more tests to overflow * Adding all tests for overflow * making changes to camel case in config * Adding information about parameters and docstring * removing compute_mel_statistics moved statistic computation to the model instead * Added overflow in readme * Adding more test cases, now it doesn't saves transition_p like tensor and can be dumped as json
🐸💬 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 💪.