Skip to content

pytorch implementation for MultiSpeech: Multi-Speaker Text to Speech with Transformer paper

License

Notifications You must be signed in to change notification settings

msalhab96/MultiSpeech

Folders and files

NameName
Last commit message
Last commit date

Latest commit

e7d19f9 · Jun 23, 2022

History

54 Commits
Jun 12, 2022
Jun 12, 2022
Jun 22, 2022
Jun 23, 2022
Jun 22, 2022
Jun 22, 2022
Jun 21, 2022
Jun 19, 2022
Jun 21, 2022
Jun 19, 2022
Jun 22, 2022
Jun 22, 2022
Jun 19, 2022
Jun 22, 2022
Jun 22, 2022
Jun 22, 2022
Jun 12, 2022
Jun 19, 2022
Jun 22, 2022
Jun 20, 2022

Repository files navigation

MultiSpeech

This is a PyTorch implementation of MultiSpeech: Multi-Speaker Text to Speech with Transformer

model

Train on your data

In order to train the model on your data, follow the steps below

1. data preprocessing

  • prepare your data and make sure the data is formatted in an PSV format as below without the header
speaker_id,audio_path,text,duration
0|file/to/file.wav|the text in that file|3.2 

The speaker id should be integer and starts from 0

  • make sure the audios are MONO if not make the proper conversion to meet this condition

2. Setup development environment

  • create enviroment
python -m venv env
  • activate the enviroment
source env/bin/activate
  • install the required dependencies
pip install -r requirements.txt

3. Training

  • update the config file if needed
  • train the model
    python train.py --train_path train_data.txt --test_path test_data.txt --checkpoint_dir outdir --epoch 100 --batch_size 64

About

pytorch implementation for MultiSpeech: Multi-Speaker Text to Speech with Transformer paper

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages