# multitarget-voice-conversion-vctk

**Repository Path**: lijiong16/multitarget-voice-conversion-vctk

## Basic Information

- **Project Name**: multitarget-voice-conversion-vctk
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: vctk-train
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-05-13
- **Last Updated**: 2021-05-13

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Voice conversion via disentangle context representation (Code for paper:https://arxiv.org/pdf/1804.02812.pdf )

Steps for training:
1.) Use make_dataset_vctk.py to convert the VCTK corpus into training data.
2.) Use make_single_samples.py to make the data feed dictionary/log used in training.
3.) Train using main.py
4.) Generate converted samples using convert.py