portfoliopage.ameureka.com

Refer to

参看本地训练：https://github.com/Plachtaa/VITS-fast-fine-tuning/blob/main/LOCAL.md
参考演示： https://huggingface.co/spaces/kira4424/VITS-fast-fine-tuning

Install

pyenv virtualenv 3.10.6 vits
pyenv activate vits
git clone https://github.com/Plachtaa/VITS-fast-fine-tuning.git
pip install -r requirements.txt
pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118

Uninstalling torchaudio-2.1.0:
Successfully uninstalled torchaudio-2.1.0
Successfully installed cmake-3.25.0 lit-15.0.7 torch-2.0.0+cu118 torchaudio-2.0.1+cu118 torchvision-0.15.1+cu118 triton-2.0.0

cp exam1.c /usr/ wang/
python scripts/video2audio.py python scripts/denoise_audio
python scripts/long_audio_transcribe.py --languages "{C}" --whisper_size large
python scripts/short_audio_transcribe.py --languages "{C}" --whisper_size large
python scripts/resample.pypython preprocess_v2.py --languages "{C}"

python finetune_speaker_v2.py -m ./OUTPUT_MODEL --max_epochs "{3000}" --drop_speaker_embed True
tensorboard --logdir=./OUTPUT_MODEL
cp ./configs/modified_finetune_speaker.json ./finetune_speaker.json
python VC_inference.py --model_dir ./OUTPUT_MODEL/G_latest.pth --share True

Installation Process

You can follow the next steps to install the repo.