0. Description
RTVC-7 Voice Cloning Model
demo: https://blue-fish.github.io/experiments/RTVC-7.html
- Run RealTime VoiceClone on Git: https://github.com/CorentinJ/Real-Time-Voice-Cloning
- Simplify it, write it in Git: https://github.com/ruclion/Pretrained-EarSpeech
1. Git Clone
- git clone https://github.com/CorentinJ/Real-Time-Voice-Cloning.git
- mv Real-Time-Voice-Cloning Pretrained-EarSpeech
- cd Pretrained-EarSpeech
- git init
- git add .
- git commit -m 'init'
- git remote add origin https://github.com/ruclion/Pretrained-EarSpeech.git
- 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
- Download to Pretrained-EarSpeech folder
- unzip pretrained.zip
The design is better, and it is directly decompressed in the corresponding position
4. Test Configuration
- python demo_cli.py --no_sound
- /ceph/home/hujk17/Pretrained-EarSpeech/samples/1320_00000.mp3
- I like Pretrained Ear Speech and China, salute
5. Commit version
https://github.com/ruclion/Pretrained-EarSpeech/commit/81428b30a486314577bfbd59b272d7e4bd369ef4