foamliu/Tacotron2-Mandarin

PyTorch reimplementation of Tacotron2 in Mandarin

Tacotron 2

A PyTorch implementation of Tacotron2, described in Natural TTS Synthesis By Conditioning Wavenet On Mel Spectrogram Predictions, an end-to-end text-to-speech(TTS) neural network architecture, which directly converts character text sequence to speech.

Dataset

BZNSYP Dataset

Dependency

• Python 3.6.8
• PyTorch 1.3.0

Usage

Data Pre-processing

Extract data:

$ python extract.py

Train

$ python train.py

If you want to visualize during training, run in your terminal:

$ tensorboard --logdir runs

Demo

Generate mel-spectrogram for text "相对论直接和间接的催生了量子力学的诞生 也为研究微观世界的高速运动确立了全新的数学模型"

$ python demo.py

audio sample

小小的赞助~

若对您有帮助可给予小小的赞助~