German Tacotron 2 and Multi-band MelGAN in TensorFlow with TF Lite inference support
Python module to clean and transliterate (i.e. normalize) German text including abbreviations, numbers, timestamps etc. It can be used to clean messy text (e.g. map peculiar Unicode encodings to ASCII) or replace common abbreviations in text in combination with various text mining tasks.
:stuck_out_tongue_closed_eyes: TensorflowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2