Three steps of Cross-Lingual TTS based on RTVC-7 Voice Cloning Model: The first step is to build Pretrained-EarSpeech

0. Description

RTVC-7 Voice Cloning Model

demo: https://blue-fish.github.io/experiments/RTVC-7.html

1. Run RealTime VoiceClone on Git:  https://github.com/CorentinJ/Real-Time-Voice-Cloning
2. Simplify it, write it in Git:  https://github.com/ruclion/Pretrained-EarSpeech

1. Git Clone

1. git clone https://github.com/CorentinJ/Real-Time-Voice-Cloning.git
2. mv Real-Time-Voice-Cloning Pretrained-EarSpeech
3. cd Pretrained-EarSpeech
4. git init
5. git add .
6. git commit -m 'init'
7. git remote add origin https://github.com/ruclion/Pretrained-EarSpeech.git
8.  git push -u origin master

2. Install Requirements

• booksa> = 0.8.0
• matplotlib>=3.3.0
• numpy==1.19.4
• scipy>=1.0.0
• SoundFile
• Unidecode
• inflect
• numba

3. Download Pretrained Models

3.1 Download page

https://github.com/CorentinJ/Real-Time-Voice-Cloning/wiki/Pretrained-models

3.2. Pretrained description

https://blue-fish.github.io/experiments/RTVC-7.html

3.3. Steps

1. Download to Pretrained-EarSpeech folder
2. unzip pretrained.zip

The design is better, and it is directly decompressed in the corresponding position

4. Test Configuration

1.  python demo_cli.py --no_sound
2. /ceph/home/hujk17/Pretrained-EarSpeech/samples/1320_00000.mp3
3. I like Pretrained Ear Speech and China, salute

5. Commit version

https://github.com/ruclion/Pretrained-EarSpeech/commit/81428b30a486314577bfbd59b272d7e4bd369ef4