PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.
text-to-speech deep-learning efficiency pytorch tts speech-synthesis autoregressive multi-speaker robustness comprehensive tacotron single-speaker neural-tts tacotron2 reduction-factor hifi-gan mel-gan diagonal-guided-attention
-
Updated
Jul 31, 2023 - Python