VITS_Japanese
1.0.0
(ข้อเสนอแนะ) Python == 3.7
git clone https://github.com/CjangCjengh/vits.gitpip install -r requirements.txt"n_speakers" ควรเป็น 0 ใน config.json
path/to/XXX.wav|transcript
dataset/001.wav|こんにちは。
รหัสลำโพงควรเริ่มจาก 0
path/to/XXX.wav|speaker id|transcript
dataset/001.wav|0|こんにちは。
หากคุณทำสิ่งนี้ให้ตั้งค่า "Cleaned_Text" เป็น TRUE ใน config.json
# Single speaker
python preprocess.py --text_index 1 --filelists path/to/filelist_train.txt path/to/filelist_val.txt
# Mutiple speakers
python preprocess.py --text_index 2 --filelists path/to/filelist_train.txt path/to/filelist_val.txt cd monotonic_align
python setup.py build_ext --inplace
cd .. # Single speaker
python train.py -c < config > -m < folder >
# Mutiple speakers
python train_ms.py -c < config > -m < folder > ดู inference.ipynb
ดู Moegoe
docker run -itd --gpus all --name " Container name " -e NVIDIA_DRIVER_CAPABILITIES=compute,utility -e NVIDIA_VISIBLE_DEVICES=all " Image name "