metadata
tags:
- RVC
- RVC v2
- Applio
- RVMPE-GPU
- RVMPE
- 250Epochs
- 500Epochs
- 1000Epochs
- Cyberpunk 2077
- Voice Models
- Johnny Silverhand
license: mit
language:
- pt
Introduction:
This repository contains high quality voice models that aim to replicate the voices of Cyberpunk 2077 characters. These models can be freely used within Text To Speech (TTS) software, voice changers, or Audio to Audio software.
Currently I started with pt-br voice models.
Datasets:
All of the datasets used to train these models are:
1. Of at least 20-60 minutes long and are collected from online videos, mostly YouTube.
2. These datasets are edited to contain the best high-quality audio of the speaker's voice with no background noise, music, silence, or any artifacts.
3.The sample rate of all of these datasets are 40k hz with the training using the 40k hz.
Training:
All of the Voice Models are trained using:
1. The algorithm: RVMPE_GPU.
2. Applio
3. With pitch guidance.
4. 250-500 Total Epochs with the minimum steps reaching 1500 to max steps hitting around 6000.
5. Software used: https://github.com/IAHispano/Applio
6. All of this was done using Kaggle with 2 Tesla T4 GPU. https://www.kaggle.com/code/deiant/applio
Remember:
I don't own any of the content used for the dataset creation as well as the voice model training. As such I am not responsible for any misuse or abuse of any of this content. All of this was produced for educational purposes as well as for personal usage not malicious intent. Use these voice models at your risk and enjoy!