2021-08-07 11:56:00 +08:00
[](http://choosealicense.com/licenses/mit/)
> This repository is forked from [Real-Time-Voice-Cloning](https://github.com/CorentinJ/Real-Time-Voice-Cloning) which only support English.
> English | [中文](README-CN.md)
## Features
2021-08-13 00:41:58 +08:00
🌍 **Chinese** supported mandarin and tested with multiple datasets: aidatatang_200zh, SLR68
2021-08-07 11:56:00 +08:00
🤩 **PyTorch** worked for pytorch, tested in version of 1.9.0(latest in August 2021), with GPU Tesla T4 and GTX 2060
🌍 **Windows + Linux** tested in both Windows OS and linux OS after fixing nits
🤩 **Easy & Awesome** effect with only newly-trained synthesizer, by reusing the pretrained encoder/vocoder
2021-08-07 16:36:07 +08:00
### [DEMO VIDEO](https://www.bilibili.com/video/BV1sA411P7wM/)
2021-08-07 11:56:00 +08:00
## Quick Start
### 1. Install Requirements
> Follow the original repo to test if you got all environment ready.
**Python 3.7 or higher ** is needed to run the toolbox.
* Install [PyTorch ](https://pytorch.org/get-started/locally/ ).
* Install [ffmpeg ](https://ffmpeg.org/download.html#get-packages ).
* Run `pip install -r requirements.txt` to install the remaining necessary packages.
2021-08-11 09:51:02 +08:00
### 2. Reuse the pretrained encoder/vocoder
* Download the following models and extract to the root directory of this project. Don't use the synthesizer
2021-08-09 19:46:18 +08:00
https://github.com/CorentinJ/Real-Time-Voice-Cloning/wiki/Pretrained-models
2021-08-11 09:51:02 +08:00
> Note that we need to specify the newly trained synthesizer model, since the original model is incompatible with the Chinese sympols. It means the demo_cli is not working at this moment.
2021-08-09 19:46:18 +08:00
### 3. Train synthesizer with aidatatang_200zh
2021-08-07 11:56:00 +08:00
* Download aidatatang_200zh dataset and unzip: make sure you can access all .wav in *train* folder
* Preprocess with the audios and the mel spectrograms:
`python synthesizer_preprocess_audio.py <datasets_root>`
2021-08-13 00:41:58 +08:00
Allow parameter `--dataset {dataset}` to support adatatang_200zh, SLR68
2021-08-07 11:56:00 +08:00
* Preprocess the embeddings:
`python synthesizer_preprocess_embeds.py <datasets_root>/SV2TTS/synthesizer`
* Train the synthesizer:
`python synthesizer_train.py mandarin <datasets_root>/SV2TTS/synthesizer`
* Go to next step when you see attention line show and loss meet your need in training folder *synthesizer/saved_models/* .
> FYI, my attention came after 18k steps and loss became lower than 0.4 after 50k steps.
2021-08-07 12:02:34 +08:00
2021-08-07 11:56:00 +08:00
2021-08-09 19:46:18 +08:00
### 4. Launch the Toolbox
2021-08-07 11:56:00 +08:00
You can then try the toolbox:
`python demo_toolbox.py -d <datasets_root>`
or
`python demo_toolbox.py`
2021-08-16 22:22:55 +08:00
> Good news🤩: Chinese Characters are supported
2021-08-07 11:56:00 +08:00
## TODO
2021-08-07 16:36:07 +08:00
- [x] Add demo video
2021-08-13 00:41:58 +08:00
- [X] Add support for more dataset
2021-08-07 16:36:07 +08:00
- [ ] Upload pretrained model
2021-08-07 11:56:00 +08:00
- 🙏 Welcome to add more
