Skip to content

PravalX/TTS_Piper

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

4 Commits
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

Piper TTS pipeline

This repository contains a complete pipeline for training, preprocessing, and exporting a custom Text-to-Speech (TTS) model. It covers data preparation, model training, and ONNX export for deployment purposes.

๐Ÿ“ Project Structure

File Description
TTS_dataset_preprocess.ipynb Preprocesses the audio and text data into a format suitable for training
TTS_custom_training.ipynb Trains the TTS model using a specified configuration and dataset
TTS_export.ipynb Exports the trained model to ONNX format for inference or deployment

๐Ÿš€ Features

  • Preprocessing of raw datasets into JSONL format
  • Configuration-driven model training using PyTorch
  • ONNX export for runtime-efficient deployment
  • Modular and customizable pipeline

๐Ÿ› ๏ธ Requirements

Make sure to install the Python dependencies especially all dependencies in the depend.py.

Models Location

You can find out the models at https://huggingface.co/rhasspy/piper-voices or https://github.com/rhasspy/piper/blob/master/VOICES.md.

About

No description, website, or topics provided.

Resources

License

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors