To check the current status, see this.

This is a tensorflow implementation of DEEP VOICE 3: 2000-SPEAKER NEURAL TEXT-TO-SPEECH. For now I'm focusing on single speaker synthesis.

I'm trying with Nick Offerman's audiobook files for fun and The LJ Speech Dataset which in public domain.

• hyperparams.py: hyper parameters
• prepro.py: creates inputs and targets, i.e., mel spectrogram, magnitude, and dones.
• data_load.py
• utils.py: several custom operational functions.
• modules.py: building blocks for the networks.
• networks.py: encoder, decoder, and converter
• train.py: train
• synthesize.py: inference
• test_sents.txt: some test sentences in the paper.

• Fitting New Speakers Based on a Short Untranscribed Sample