https://github.com/PiSchool/mxnet-tacotron

https://github.com/PiSchool/mxnet-tacotron

Last synced: 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/PiSchool/mxnet-tacotron
• Owner: PiSchool
• Created: 2017-10-27T14:55:38.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2017-12-18T16:12:10.000Z (about 7 years ago)
• Last Synced: 2024-08-01T22:41:50.991Z (5 months ago)
• Language: Python
• Size: 3.94 MB
• Stars: 10
• Watchers: 4
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-MXNet - Tacotron

README

        
# Tacotron over MXNet

A tech demo of MXNet capabilities consisting of a Tacotron implementation. This is a work in progress. 

This project was made during the 8 weeks from 10-2017 to 12-2017 at the PiCampus AI School in Rome.

## List of functionalities and TODOs

- [x] Multithreading data iterator

- [x] DSP tools 

- [x] CBHG module for spectrograms

- [x] Basic seq2seq example for string reverse. It we'll be used as Tacotron backbone

- [ ] Encoder with CBHG 

- [ ] Attention model

- [ ] Custom decoder for processing r * mel_bands spectrograms frames for each time step during the cell unrolling  

- [ ] Switch to MXNet 1.0

- [ ] Switch to Gluon

- [ ] Clean up and organize code for better understanding

## Getting Started

* install MXNet: 

 pip install -r requirements.txt 

* run:

 python tacotron.py 

Using the default setting, a simple dataset will be used as training. Predictions samples will be generated at the end of the training phase.

If you want to train over a big dataset, Kyubyong has cut and formatted  this  English bible. You can find his dataset   here  and the CSV text here . 

### Prerequisites

This project has been developed on 

- MXNet 0.12

- librosa

## Authors

This project was developed by [Alberto Massidda](https://github.com/aijanai) and [Stefano Artuso](https://github.com/nefastosaturo) during [Pi School's AI programme](http://picampus-school.com/programme/school-of-ai/) in Fall 2017.

 

![photo of Alberto Massidda](http://picampus-school.com/wp-content/uploads/2017/11/IMG_2125-2-150x150.jpg) ![photo of Stefano Artuso](http://picampus-school.com/wp-content/uploads/2017/11/IMG_2043-2-150x150.jpg)

## Acknowledgments

* Thanks to Roberto Barra Chicote for supporting us

* Thanks to Keith Ito https://github.com/keithito, Kyubyong Park https://github.com/Kyubyong for making us start diving in