A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
MIT License
Clone a voice in 5 seconds to generate arbitrary speech in real-time
DeepMind's Tacotron-2 Tensorflow implementation
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
Deep Speaker: an End-to-End Neural Speaker Embedding System.
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
Application of Connectionist Temporal Classification (CTC) for Speech Recognition (Tensorflow 1.0...