Retrieval_based_Voice_Conversion_WebUI.ipynb
# @title 查看显卡
!nvidia-smi
# @title 挂载谷歌云盘
from google.colab import drive
drive.mount("/content/drive")
# @title 安装依赖
!apt-get -y install build-essential python3-dev ffmpeg
!pip3 install --upgrade setuptools wheel
!pip3 install --upgrade pip
!pip3 install faiss-cpu==1.7.2 fairseq gradio==3.14.0 ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2
# @title 克隆仓库
!git clone --depth=1 -b stable https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI
%cd /content/Retrieval-based-Voice-Conversion-WebUI
!mkdir -p pretrained uvr5_weights
# @title 更新仓库（一般无需执行）
!git pull
# @title 安装aria2
!apt -y install -qq aria2
# @title 下载底模
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G32k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G40k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G48k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D32k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D40k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth
# @title 下载人声分离模型
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth
# @title 下载hubert_base
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt
# @title #下载rmvpe模型
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o rmvpe.pt
# @title 从谷歌云盘加载打包好的数据集到/content/dataset
# @markdown 数据集位置
DATASET = (
"/content/drive/MyDrive/dataset/lulu20230327_32k.zip" # @param {type:"string"}
)
!mkdir -p /content/dataset
!unzip -d /content/dataset -B {DATASET}
# @title 重命名数据集中的重名文件
!ls -a /content/dataset/
!rename 's/(\w+)\.(\w+)~(\d*)/$1_$3.$2/' /content/dataset/*.*~*
# @title 启动web
%cd /content/Retrieval-based-Voice-Conversion-WebUI
# %load_ext tensorboard
# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs
!python3 infer-web.py --colab --pycmd python3
# @title 手动将训练后的模型文件备份到谷歌云盘
# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名
# @markdown 模型名
MODELNAME = "lulu" # @param {type:"string"}
# @markdown 模型epoch
MODELEPOCH = 9600 # @param {type:"integer"}
!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth
!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth
!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/
!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/
!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth
# @title 从谷歌云盘恢复pth
# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名
# @markdown 模型名
MODELNAME = "lulu" # @param {type:"string"}
# @markdown 模型epoch
MODELEPOCH = 7500 # @param {type:"integer"}
!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}
!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth
!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth
!cp /content/drive/MyDrive/*.index /content/
!cp /content/drive/MyDrive/*.npy /content/
!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth
# @title 手动预处理（不推荐）
# @markdown 模型名
MODELNAME = "lulu" # @param {type:"string"}
# @markdown 采样率
BITRATE = 48000 # @param {type:"integer"}
# @markdown 使用的进程数
THREADCOUNT = 8 # @param {type:"integer"}
!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True
# @title 手动提取特征（不推荐）
# @markdown 模型名
MODELNAME = "lulu" # @param {type:"string"}
# @markdown 使用的进程数
THREADCOUNT = 8 # @param {type:"integer"}
# @markdown 音高提取算法
ALGO = "harvest" # @param {type:"string"}
!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}
!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME} True
# @title 手动训练（不推荐）
# @markdown 模型名
MODELNAME = "lulu" # @param {type:"string"}
# @markdown 使用的GPU
USEGPU = "0" # @param {type:"string"}
# @markdown 批大小
BATCHSIZE = 32 # @param {type:"integer"}
# @markdown 停止的epoch
MODELEPOCH = 3200 # @param {type:"integer"}
# @markdown 保存epoch间隔
EPOCHSAVE = 100 # @param {type:"integer"}
# @markdown 采样率
MODELSAMPLE = "48k" # @param {type:"string"}
# @markdown 是否缓存训练集
CACHEDATA = 1 # @param {type:"integer"}
# @markdown 是否仅保存最新的ckpt文件
ONLYLATEST = 0 # @param {type:"integer"}
!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}
# @title 删除其它pth，只留选中的（慎点，仔细看代码）
# @markdown 模型名
MODELNAME = "lulu" # @param {type:"string"}
# @markdown 选中模型epoch
MODELEPOCH = 9600 # @param {type:"integer"}
!echo "备份选中的模型。。。"
!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth
!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth
!echo "正在删除。。。"
!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}
!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth
!echo "恢复选中的模型。。。"
!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth
!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth
!echo "删除完成"
!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}
# @title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）
# @markdown 模型名
MODELNAME = "lulu" # @param {type:"string"}
# @markdown 选中模型epoch
MODELEPOCH = 9600 # @param {type:"integer"}
!echo "备份选中的模型。。。"
!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth
!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth
!echo "正在删除。。。"
!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}
!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*
!echo "恢复选中的模型。。。"
!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth
!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth
!echo "删除完成"
!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}