Pytorch implementation of Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
This implementation focuses as much as possible on the readability and extensibility of the code and the reproduction as it is in the paper (without Wavenet). I would appreciate it if you could feedback or contribution at any time if there was a mistake or an error.
import torch
import numpy as np
from tacotron2 import Tacotron2
from test.args import DefaultArgument
batch_size, seq_length = 3, 3
inputs = torch.LongTensor(np.arange(batch_size * seq_length).reshape(batch_size, seq_length))
input_lengths = torch.LongTensor([3, 3, 2])
targets = torch.FloatTensor(batch_size, 100, 80).uniform_(-0.1, 0.1)
args = DefaultArgument()
model = Tacotron2(args)
output = model(inputs, targets, input_lengths)
Currently we only support installation from source code using setuptools. Checkout the source code and run the following commands:
pip install -e .
If you have any questions, bug reports, and feature requests, please open an issue on github or
contacts [email protected] please.
I appreciate any kind of feedback or contribution. Feel free to proceed with small issues like bug fixes, documentation improvement. For major contributions and new features, please discuss with the collaborators in corresponding issues.
I follow PEP-8 for code style. Especially the style of docstrings is important to generate documentation.
- Soohwan Kim @sooftware
- Contacts: [email protected]