|- convert*.py (convert target torch model to TF.) |- compute_statistics.py (compute dataset statistics for normalization.) |- distribute.py (train your TTS model using Multiple GPUs.) |- bin/ (folder for all the executables.) |- notebooks/ (Jupyter Notebooks for model evaluation, parameter selection and data analysis.) If you are only interested in synthesizing speech with the released TTS models, installing from PyPI is the easiest option. You can also help us implement more models. Modular (but not too much) code base enabling easy testing for new ideas.Notebooks for extensive model benchmarking.Tools to curate Text2Speech datasets under dataset_analysis.Released models in PyTorch, Tensorflow and TFLite.Ability to convert PyTorch models to Tensorflow 2.0 and TFLite for inference.Detailed training logs on console and Tensorboard.Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN).Speaker Encoder to compute speaker embeddings efficiently.Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech).High performance Deep Learning models for Text2Speech tasks.Help is much more valuable if it's shared publicly, so that more people can benefit from it. Please use our dedicated channels for questions and discussion. □ Text-to-Speech paper collection □ Where to ask questions □ English Voice Samples and SoundCloud playlist TTS comes with pretrained models, tools for measuring dataset quality and already used in 20+ languages for products and research projects. It's built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed and quality. TTS is a library for advanced Text-to-Speech generation.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |