Experimental Released Models

English

TTS Models	Dataset	Commit	Audio Sample	Details
Tacotron2	LJSpeech	branch	---	Details
Tacotron2 DDC	LJSpeech	72a6ac5	voice samples	Trained with DDC and includes PyTorch, Tensorflow and TFLite models. Check Colab notebooks or notebooks folder.
Glow-TTS	LJSpeech	08394e4	---	Details. Sample notebook
Multi-Speaker-Tacotron2	VCTK	4873601	Colab notebook	Multi-Speaker TTS model with Tacotron2/
Multi-Speaker-Tacotron2 DDC	VCTK	2136433	Colab notebook	Multi-Speaker TTS model with Tacotron2 and Double Decoder Consistency.
Tacotron2 with Dynamic Conv Attention	LJSpeech	4132240	Colab notebook	Tacotron2 with Dynamic Convolutional Attention.
Glow-TTS	LJSpeech	4132240	Colab notebook	Glow-TTS as in the paper.

Speaker Encoder Models	Dataset	Commit
Speaker-Encoder-iter25k	LibriSpeech	...
Speaker-Encoder by @mueller91	LibriTTS + VCTK + VoxCeleb + CommonVoice	...

Vocoder Models	Dataset	Commit	Details
ParallelWaveGAN	LJSpeech	72a6ac5	Trained using TTS.vocoder. It produces better results than MelGAN model but it is slightly slower. Check notebooks for testing.
Multi-Band MelGAN	LJSpeech	72a6ac5	Trained using TTS.vocoder. It is the fastest vocoder model. Check notebooks for testing.
WaveRNN models			go to repo for the models. (Soon to be deprecated)
Full-Band MelGAN	LibriTTS	c514628	Trained using TTS.vocoder. Generic vocoder that can sample any voice. Sampling rate 24Khz. To use with a different sampling rate follow this issue.
Universal WaveGrad	LibriTTS	2136433	Trained using TTS.vocoder. Generic vocoder that can sample any voice. Original Sampling rate 24Khz. To use with a different sampling rate follow this issue.
Universal HifiGAN	LibriTTS	-

Simple packaging - self-contained package that runs an HTTP API for a pre-trained TTS model

How to use:

1. Create a fresh virtual environment with Python 3.6
2. $ apt-get install espeak libsndfile1
3. $ pip install python_package_url_from_table_below
4. $ python -m TTS.server.server
5. Open http://localhost:5002

Model	Dataset	Python package	nginx/uWSGI config files
Tacotron 2 + Forward Attention + PWGAN	LJSpeech	TTS-0.0.1+92aea2a-py3-none-any.whl	tts-nginx-uwsgi.zip

The server is a Flask application. For deployment with multiple workers see the nginx/uWSGI config files also linked in the table above. Pass --use_cuda 1 to use GPUs when available.

Spanish

TTS Models	Dataset	Commit	Audio Sample	Details
Tacotron2 DDC	MAI-Labs	48a40c4	---	Model Details and Colab Notebook.

French

TTS Models	Dataset	Commit	Audio Sample	Details
Tacotron2 DDC	MAI-Labs	f09defa	---	Model Details and Colab Notebook.

German

German Model Colab Example

Portuguese

model details by @Edresson