🐸TTS is a library for advanced Text-to-Speech generation. It’s built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed and quality. 🐸TTS comes with pretrained models, tools for measuring dataset quality and already used in 20+ languages for products and research projects.
💬 Where to ask questions¶
Please use our dedicated channels for questions and discussion. Help is much more valuable if it’s shared publicly so that more people can benefit from it.
🥇 TTS Performance¶
Underlined “TTS*” and “Judy*” are 🐸TTS models
High-performance Deep Learning models for Text2Speech tasks.
Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech).
Speaker Encoder to compute speaker embeddings efficiently.
Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN)
Fast and efficient model training.
Detailed training logs on the terminal and Tensorboard.
Support for Multi-speaker TTS.
Efficient, flexible, lightweight but feature complete
Ability to convert PyTorch models to Tensorflow 2.0 and TFLite for inference.
Released and read-to-use models.
Tools to curate Text2Speech datasets under
Utilities to use and test your models.
Modular (but not too much) code base enabling easy implementation of new ideas.
🐸TTS is tested on Ubuntu 18.04 with python >= 3.6, < 3.9.
If you are only interested in synthesizing speech with the released 🐸TTS models, installing from PyPI is the easiest option.
pip install TTS
By default, this only installs the requirements for PyTorch. To install the tensorflow dependencies as well, use the
pip install TTS[tf]
If you plan to code or train models, clone 🐸TTS and install it locally.
git clone https://github.com/coqui-ai/TTS pip install -e .[all,dev,notebooks,tf] # Select the relevant extras
If you are on Ubuntu (Debian), you can also run following commands for installation.
$ make system-deps # intended to be used on Ubuntu (Debian). Let us know if you have a diffent OS. $ make install
If you are on Windows, 👑@GuyPaddock wrote installation instructions here.
|- notebooks/ (Jupyter Notebooks for model evaluation, parameter selection and data analysis.) |- utils/ (common utilities.) |- TTS |- bin/ (folder for all the executables.) |- train*.py (train your target model.) |- distribute.py (train your TTS model using Multiple GPUs.) |- compute_statistics.py (compute dataset statistics for normalization.) |- convert*.py (convert target torch model to TF.) |- ... |- tts/ (text to speech models) |- layers/ (model layer definitions) |- models/ (model definitions) |- tf/ (Tensorflow 2 utilities and model implementations) |- utils/ (model specific utilities.) |- speaker_encoder/ (Speaker Encoder models.) |- (same) |- vocoder/ (Vocoder models.) |- (same)
- Tutorial For Nervous Beginners
- Humble FAQ
- Errors with a pre-trained model. How can I resolve this?
- What are the requirements of a good 🐸TTS dataset?
- How should I choose the right model?
- How can I train my own
- How can I train in a different language?
- How can I train multi-GPUs?
- How can I check model performance?
- How do I know when to stop training?
- My model does not learn. How can I debug?
- Attention does not align. How can I make it work?
- How can I test a trained model?
- My Tacotron model does not stop - I see “Decoder stopped with ‘max_decoder_steps” - Stopnet does not work.
- Contribution guidelines
- Synthesizing Speech
- Implementing a Model
- Training a Model
- Formatting Your Dataset
- What makes a good TTS dataset
- TTS Datasets
- Converting Torch to TF 2