The Implementation of FastSpeech Based on Pytorch.

• FastSpeech Reading Notes(Chinese)
• Details of this Implementation

1. Download and extract LJSpeech dataset.
2. Put LJSpeech dataset in data.
3. Run preprocess.py.
4. If you want to get the target of alignment before training(It will speed up the training process greatly), you need download the pre-trained Tacotron2 model published by NVIDIA here. The outputs of mel spectrogram and alignment are shown as follow:

• python 3.6
• pytorch 1.1.0
• numpy 1.16.2
• scipy 1.2.1
• librosa 0.6.3
• inflect 2.1.0
• matplotlib 2.2.2

• If you don't prepare the target of alignment before training, the process of training would be very long.
• In the paper of Transformer-TTS, authors use pre-trained Transformer-TTS to provide the target of alignment. I didn't have a well-trained Transformer-TTS model so I use Tacotron2 instead.
• If you want to use another model to get targets of alignment, you need rewrite alignment.py.
• The returned value of alignment.py is a tensor whose value is the multiple that encoder's outputs are supposed to be expanded by.
• For example:

test_target = torch.stack([torch.Tensor([0, 2, 3, 0, 3, 2, 1, 0, 0, 0]),
                           torch.Tensor([1, 2, 3, 2, 2, 0, 3, 6, 3, 5])])

• The Implementation of Tacotron Based on Tensorflow
• The Implementation of Transformer Based on Pytorch
• The Implementation of Transformer-TTS Based on Pytorch
• The Implementation of Tacotron2 Based on Pytorch