mirror of
https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-06-05 01:10:22 +08:00
feat(all): optimize hierarchy of files
This commit is contained in:
源文雨
353
tools/ipynb/v1.ipynb
Normal file
353
tools/ipynb/v1.ipynb
Normal file
@@ -0,0 +1,353 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "WHBMn6dOWm-S"
|
||||
},
|
||||
"source": [
|
||||
"# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "ZFFCx5J80SGa"
|
||||
},
|
||||
"source": [
|
||||
"[](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/tools/colab/v1.ipynb)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "GmFP6bN9dvOq"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 查看显卡\n",
|
||||
"!nvidia-smi"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "jwu07JgqoFON"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 挂载谷歌云盘\n",
|
||||
"\n",
|
||||
"from google.colab import drive\n",
|
||||
"\n",
|
||||
"drive.mount(\"/content/drive\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "wjddIFr1oS3W"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 安装依赖\n",
|
||||
"!apt -y install build-essential python3-dev ffmpeg\n",
|
||||
"!pip3 install --upgrade setuptools wheel\n",
|
||||
"!pip3 install --upgrade pip"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "ge_97mfpgqTm"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 克隆仓库\n",
|
||||
"\n",
|
||||
"!git clone --depth=1 -b v1 https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI\n",
|
||||
"%cd /content/Retrieval-based-Voice-Conversion-WebUI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "BLDEZADkvlw1"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 安装依赖\n",
|
||||
"!pip install -r requirements.txt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "pqE0PrnuRqI2"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 下载安装 RVC-Models-Downloader\n",
|
||||
"!wget https://github.com/RVC-Project/RVC-Models-Downloader/releases/download/v0.2.1/rvcmd_linux_amd64.deb\n",
|
||||
"!apt install ./rvcmd_linux_amd64.deb"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "UG3XpUwEomUz"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 下载所需资源\n",
|
||||
"!rvcmd -notrs -w 1 -notui assets/v1\n",
|
||||
"!rvcmd -notrs -w 1 -notui assets/rmvpe"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "Mwk7Q0Loqzjx"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 从谷歌云盘加载打包好的数据集到/content/dataset\n",
|
||||
"\n",
|
||||
"# @markdown 数据集位置\n",
|
||||
"DATASET = \"/content/drive/MyDrive/mydataset.zip\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"!mkdir -p /content/dataset\n",
|
||||
"!unzip -d /content/dataset -B {DATASET}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "PDlFxWHWEynD"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 重命名数据集中的重名文件\n",
|
||||
"!ls -a /content/dataset/\n",
|
||||
"!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "7vh6vphDwO0b"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 启动web\n",
|
||||
"%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
|
||||
"# %load_ext tensorboard\n",
|
||||
"# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
|
||||
"!python3 infer-web.py --colab --pycmd python3"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "FgJuNeAwx5Y_"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 手动将训练后的模型文件备份到谷歌云盘\n",
|
||||
"# @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\n",
|
||||
"\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 模型epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
|
||||
"\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "OVQoLQJXS7WX"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 从谷歌云盘恢复pth\n",
|
||||
"# @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\n",
|
||||
"\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 模型epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
|
||||
"\n",
|
||||
"!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/drive/MyDrive/*.index /content/\n",
|
||||
"!cp /content/drive/MyDrive/*.npy /content/\n",
|
||||
"!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "ZKAyuKb9J6dz"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 手动预处理（不推荐）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 采样率\n",
|
||||
"BITRATE = 48000 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 使用的进程数\n",
|
||||
"THREADCOUNT = 8 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "CrxJqzAUKmPJ"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 手动提取特征（不推荐）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 使用的进程数\n",
|
||||
"THREADCOUNT = 8 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 音高提取算法\n",
|
||||
"ALGO = \"harvest\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
|
||||
"\n",
|
||||
"!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME} True"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "IMLPLKOaKj58"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 手动训练（不推荐）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 使用的GPU\n",
|
||||
"USEGPU = \"0\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 批大小\n",
|
||||
"BATCHSIZE = 32 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 停止的epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 保存epoch间隔\n",
|
||||
"EPOCHSAVE = 100 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 采样率\n",
|
||||
"MODELSAMPLE = \"48k\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 是否缓存训练集\n",
|
||||
"CACHEDATA = 1 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 是否仅保存最新的ckpt文件\n",
|
||||
"ONLYLATEST = 0 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!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}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "haYA81hySuDl"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 选中模型epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!echo \"备份选中的模型。。。\"\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
|
||||
"\n",
|
||||
"!echo \"正在删除。。。\"\n",
|
||||
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
|
||||
"!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
|
||||
"\n",
|
||||
"!echo \"恢复选中的模型。。。\"\n",
|
||||
"!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
|
||||
"!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
|
||||
"\n",
|
||||
"!echo \"删除完成\"\n",
|
||||
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "QhSiPTVPoIRh"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 选中模型epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!echo \"备份选中的模型。。。\"\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
|
||||
"\n",
|
||||
"!echo \"正在删除。。。\"\n",
|
||||
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
|
||||
"!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
|
||||
"\n",
|
||||
"!echo \"恢复选中的模型。。。\"\n",
|
||||
"!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
|
||||
"!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
|
||||
"\n",
|
||||
"!echo \"删除完成\"\n",
|
||||
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"private_outputs": true,
|
||||
"provenance": []
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"name": "python"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 0
|
||||
}
|
||||
352
tools/ipynb/v2.ipynb
Normal file
352
tools/ipynb/v2.ipynb
Normal file
@@ -0,0 +1,352 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "QTSdqTqGcbyr"
|
||||
},
|
||||
"source": [
|
||||
"# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "ZFFCx5J80SGa"
|
||||
},
|
||||
"source": [
|
||||
"[](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/tools/colab/v2.ipynb)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "GmFP6bN9dvOq"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title #查看显卡\n",
|
||||
"!nvidia-smi"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "jwu07JgqoFON"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 挂载谷歌云盘\n",
|
||||
"\n",
|
||||
"from google.colab import drive\n",
|
||||
"\n",
|
||||
"drive.mount(\"/content/drive\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "wjddIFr1oS3W"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title #安装依赖\n",
|
||||
"!apt -y install build-essential python3-dev ffmpeg\n",
|
||||
"!pip3 install --upgrade setuptools wheel\n",
|
||||
"!pip3 install --upgrade pip"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "ge_97mfpgqTm"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title #克隆仓库\n",
|
||||
"\n",
|
||||
"!git clone --depth=1 -b v2.2 https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI\n",
|
||||
"%cd /content/Retrieval-based-Voice-Conversion-WebUI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "BLDEZADkvlw1"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 安装依赖\n",
|
||||
"!pip install -r requirements.txt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "pqE0PrnuRqI2"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 下载安装 RVC-Models-Downloader\n",
|
||||
"!wget https://github.com/RVC-Project/RVC-Models-Downloader/releases/download/v0.2.1/rvcmd_linux_amd64.deb\n",
|
||||
"!apt install ./rvcmd_linux_amd64.deb"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "UG3XpUwEomUz"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 下载所需资源\n",
|
||||
"!rvcmd -notrs -w 1 -notui assets/all"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "Mwk7Q0Loqzjx"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title #从谷歌云盘加载打包好的数据集到/content/dataset\n",
|
||||
"\n",
|
||||
"# @markdown 数据集位置\n",
|
||||
"DATASET = \"/content/drive/MyDrive/mydataset.zip\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"!mkdir -p /content/dataset\n",
|
||||
"!unzip -d /content/dataset -B {DATASET}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "PDlFxWHWEynD"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title #重命名数据集中的重名文件\n",
|
||||
"!ls -a /content/dataset/\n",
|
||||
"!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "7vh6vphDwO0b"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title #启动webui\n",
|
||||
"%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
|
||||
"# %load_ext tensorboard\n",
|
||||
"# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
|
||||
"!python3 infer-web.py --colab --pycmd python3"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "FgJuNeAwx5Y_"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title #手动将训练后的模型文件备份到谷歌云盘\n",
|
||||
"# @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\n",
|
||||
"\n",
|
||||
"# @markdown #模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown #模型epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
|
||||
"\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "OVQoLQJXS7WX"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 从谷歌云盘恢复pth\n",
|
||||
"# @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\n",
|
||||
"\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 模型epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
|
||||
"\n",
|
||||
"!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/drive/MyDrive/*.index /content/\n",
|
||||
"!cp /content/drive/MyDrive/*.npy /content/\n",
|
||||
"!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "ZKAyuKb9J6dz"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 手动预处理（不推荐）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 采样率\n",
|
||||
"BITRATE = 48000 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 使用的进程数\n",
|
||||
"THREADCOUNT = 8 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "CrxJqzAUKmPJ"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 手动提取特征（不推荐）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 使用的进程数\n",
|
||||
"THREADCOUNT = 8 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 音高提取算法\n",
|
||||
"ALGO = \"harvest\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
|
||||
"\n",
|
||||
"!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME} True"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "IMLPLKOaKj58"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 手动训练（不推荐）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 使用的GPU\n",
|
||||
"USEGPU = \"0\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 批大小\n",
|
||||
"BATCHSIZE = 32 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 停止的epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 保存epoch间隔\n",
|
||||
"EPOCHSAVE = 100 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 采样率\n",
|
||||
"MODELSAMPLE = \"48k\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 是否缓存训练集\n",
|
||||
"CACHEDATA = 1 # @param {type:\"integer\"}\n",
|
||||
"# @markdown 是否仅保存最新的ckpt文件\n",
|
||||
"ONLYLATEST = 0 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!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}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "haYA81hySuDl"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 选中模型epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!echo \"备份选中的模型。。。\"\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
|
||||
"\n",
|
||||
"!echo \"正在删除。。。\"\n",
|
||||
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
|
||||
"!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
|
||||
"\n",
|
||||
"!echo \"恢复选中的模型。。。\"\n",
|
||||
"!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
|
||||
"!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
|
||||
"\n",
|
||||
"!echo \"删除完成\"\n",
|
||||
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "QhSiPTVPoIRh"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
|
||||
"# @markdown 模型名\n",
|
||||
"MODELNAME = \"mymodel\" # @param {type:\"string\"}\n",
|
||||
"# @markdown 选中模型epoch\n",
|
||||
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
|
||||
"\n",
|
||||
"!echo \"备份选中的模型。。。\"\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
|
||||
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
|
||||
"\n",
|
||||
"!echo \"正在删除。。。\"\n",
|
||||
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
|
||||
"!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
|
||||
"\n",
|
||||
"!echo \"恢复选中的模型。。。\"\n",
|
||||
"!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
|
||||
"!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
|
||||
"\n",
|
||||
"!echo \"删除完成\"\n",
|
||||
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"private_outputs": true,
|
||||
"provenance": []
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"name": "python"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 0
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
import soundfile
|
||||
|
||||
from ..infer.lib.infer_pack.onnx_inference import OnnxRVC
|
||||
from infer.lib.infer_pack.onnx_inference import OnnxRVC
|
||||
|
||||
hop_size = 512
|
||||
sampling_rate = 40000 # 采样率
|
||||
@@ -1,445 +0,0 @@
|
||||
from io import BytesIO
|
||||
import os
|
||||
import pickle
|
||||
import sys
|
||||
import traceback
|
||||
from infer.lib import jit
|
||||
from infer.lib.jit.get_synthesizer import get_synthesizer
|
||||
from time import time as ttime
|
||||
import fairseq
|
||||
import faiss
|
||||
import numpy as np
|
||||
import parselmouth
|
||||
import pyworld
|
||||
import scipy.signal as signal
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torchcrepe
|
||||
|
||||
from infer.lib.infer_pack.models import (
|
||||
SynthesizerTrnMs256NSFsid,
|
||||
SynthesizerTrnMs256NSFsid_nono,
|
||||
SynthesizerTrnMs768NSFsid,
|
||||
SynthesizerTrnMs768NSFsid_nono,
|
||||
)
|
||||
|
||||
now_dir = os.getcwd()
|
||||
sys.path.append(now_dir)
|
||||
from multiprocessing import Manager as M
|
||||
|
||||
from configs.config import Config
|
||||
|
||||
# config = Config()
|
||||
|
||||
mm = M()
|
||||
|
||||
|
||||
def printt(strr, *args):
|
||||
if len(args) == 0:
|
||||
print(strr)
|
||||
else:
|
||||
print(strr % args)
|
||||
|
||||
|
||||
# config.device=torch.device("cpu")########强制cpu测试
|
||||
# config.is_half=False########强制cpu测试
|
||||
class RVC:
|
||||
def __init__(
|
||||
self,
|
||||
key,
|
||||
pth_path,
|
||||
index_path,
|
||||
index_rate,
|
||||
n_cpu,
|
||||
inp_q,
|
||||
opt_q,
|
||||
config: Config,
|
||||
last_rvc=None,
|
||||
) -> None:
|
||||
"""
|
||||
初始化
|
||||
"""
|
||||
try:
|
||||
if config.dml == True:
|
||||
|
||||
def forward_dml(ctx, x, scale):
|
||||
ctx.scale = scale
|
||||
res = x.clone().detach()
|
||||
return res
|
||||
|
||||
fairseq.modules.grad_multiply.GradMultiply.forward = forward_dml
|
||||
# global config
|
||||
self.config = config
|
||||
self.inp_q = inp_q
|
||||
self.opt_q = opt_q
|
||||
# device="cpu"########强制cpu测试
|
||||
self.device = config.device
|
||||
self.f0_up_key = key
|
||||
self.f0_min = 50
|
||||
self.f0_max = 1100
|
||||
self.f0_mel_min = 1127 * np.log(1 + self.f0_min / 700)
|
||||
self.f0_mel_max = 1127 * np.log(1 + self.f0_max / 700)
|
||||
self.n_cpu = n_cpu
|
||||
self.use_jit = self.config.use_jit
|
||||
self.is_half = config.is_half
|
||||
|
||||
if index_rate != 0:
|
||||
self.index = faiss.read_index(index_path)
|
||||
self.big_npy = self.index.reconstruct_n(0, self.index.ntotal)
|
||||
printt("Index search enabled")
|
||||
self.pth_path: str = pth_path
|
||||
self.index_path = index_path
|
||||
self.index_rate = index_rate
|
||||
self.cache_pitch: torch.Tensor = torch.zeros(
|
||||
1024, device=self.device, dtype=torch.long
|
||||
)
|
||||
self.cache_pitchf = torch.zeros(
|
||||
1024, device=self.device, dtype=torch.float32
|
||||
)
|
||||
|
||||
if last_rvc is None:
|
||||
models, _, _ = fairseq.checkpoint_utils.load_model_ensemble_and_task(
|
||||
["assets/hubert/hubert_base.pt"],
|
||||
suffix="",
|
||||
)
|
||||
hubert_model = models[0]
|
||||
hubert_model = hubert_model.to(self.device)
|
||||
if self.is_half:
|
||||
hubert_model = hubert_model.half()
|
||||
else:
|
||||
hubert_model = hubert_model.float()
|
||||
hubert_model.eval()
|
||||
self.model = hubert_model
|
||||
else:
|
||||
self.model = last_rvc.model
|
||||
|
||||
self.net_g: nn.Module = None
|
||||
|
||||
def set_default_model():
|
||||
self.net_g, cpt = get_synthesizer(self.pth_path, self.device)
|
||||
self.tgt_sr = cpt["config"][-1]
|
||||
cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]
|
||||
self.if_f0 = cpt.get("f0", 1)
|
||||
self.version = cpt.get("version", "v1")
|
||||
if self.is_half:
|
||||
self.net_g = self.net_g.half()
|
||||
else:
|
||||
self.net_g = self.net_g.float()
|
||||
|
||||
def set_jit_model():
|
||||
jit_pth_path = self.pth_path.rstrip(".pth")
|
||||
jit_pth_path += ".half.jit" if self.is_half else ".jit"
|
||||
reload = False
|
||||
if str(self.device) == "cuda":
|
||||
self.device = torch.device("cuda:0")
|
||||
if os.path.exists(jit_pth_path):
|
||||
cpt = jit.load(jit_pth_path)
|
||||
model_device = cpt["device"]
|
||||
if model_device != str(self.device):
|
||||
reload = True
|
||||
else:
|
||||
reload = True
|
||||
|
||||
if reload:
|
||||
cpt = jit.synthesizer_jit_export(
|
||||
self.pth_path,
|
||||
"script",
|
||||
None,
|
||||
device=self.device,
|
||||
is_half=self.is_half,
|
||||
)
|
||||
|
||||
self.tgt_sr = cpt["config"][-1]
|
||||
self.if_f0 = cpt.get("f0", 1)
|
||||
self.version = cpt.get("version", "v1")
|
||||
self.net_g = torch.jit.load(
|
||||
BytesIO(cpt["model"]), map_location=self.device
|
||||
)
|
||||
self.net_g.infer = self.net_g.forward
|
||||
self.net_g.eval().to(self.device)
|
||||
|
||||
def set_synthesizer():
|
||||
if self.use_jit and not config.dml:
|
||||
if self.is_half and "cpu" in str(self.device):
|
||||
printt(
|
||||
"Use default Synthesizer model. \
|
||||
Jit is not supported on the CPU for half floating point"
|
||||
)
|
||||
set_default_model()
|
||||
else:
|
||||
set_jit_model()
|
||||
else:
|
||||
set_default_model()
|
||||
|
||||
if last_rvc is None or last_rvc.pth_path != self.pth_path:
|
||||
set_synthesizer()
|
||||
else:
|
||||
self.tgt_sr = last_rvc.tgt_sr
|
||||
self.if_f0 = last_rvc.if_f0
|
||||
self.version = last_rvc.version
|
||||
self.is_half = last_rvc.is_half
|
||||
if last_rvc.use_jit != self.use_jit:
|
||||
set_synthesizer()
|
||||
else:
|
||||
self.net_g = last_rvc.net_g
|
||||
|
||||
if last_rvc is not None and hasattr(last_rvc, "model_rmvpe"):
|
||||
self.model_rmvpe = last_rvc.model_rmvpe
|
||||
if last_rvc is not None and hasattr(last_rvc, "model_fcpe"):
|
||||
self.device_fcpe = last_rvc.device_fcpe
|
||||
self.model_fcpe = last_rvc.model_fcpe
|
||||
except:
|
||||
printt(traceback.format_exc())
|
||||
|
||||
def change_key(self, new_key):
|
||||
self.f0_up_key = new_key
|
||||
|
||||
def change_index_rate(self, new_index_rate):
|
||||
if new_index_rate != 0 and self.index_rate == 0:
|
||||
self.index = faiss.read_index(self.index_path)
|
||||
self.big_npy = self.index.reconstruct_n(0, self.index.ntotal)
|
||||
printt("Index search enabled")
|
||||
self.index_rate = new_index_rate
|
||||
|
||||
def get_f0_post(self, f0):
|
||||
if not torch.is_tensor(f0):
|
||||
f0 = torch.from_numpy(f0)
|
||||
f0 = f0.float().to(self.device).squeeze()
|
||||
f0_mel = 1127 * torch.log(1 + f0 / 700)
|
||||
f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - self.f0_mel_min) * 254 / (
|
||||
self.f0_mel_max - self.f0_mel_min
|
||||
) + 1
|
||||
f0_mel[f0_mel <= 1] = 1
|
||||
f0_mel[f0_mel > 255] = 255
|
||||
f0_coarse = torch.round(f0_mel).long()
|
||||
return f0_coarse, f0
|
||||
|
||||
def get_f0(self, x, f0_up_key, n_cpu, method="harvest"):
|
||||
n_cpu = int(n_cpu)
|
||||
if method == "crepe":
|
||||
return self.get_f0_crepe(x, f0_up_key)
|
||||
if method == "rmvpe":
|
||||
return self.get_f0_rmvpe(x, f0_up_key)
|
||||
if method == "fcpe":
|
||||
return self.get_f0_fcpe(x, f0_up_key)
|
||||
x = x.cpu().numpy()
|
||||
if method == "pm":
|
||||
p_len = x.shape[0] // 160 + 1
|
||||
f0_min = 65
|
||||
l_pad = int(np.ceil(1.5 / f0_min * 16000))
|
||||
r_pad = l_pad + 1
|
||||
s = parselmouth.Sound(np.pad(x, (l_pad, r_pad)), 16000).to_pitch_ac(
|
||||
time_step=0.01,
|
||||
voicing_threshold=0.6,
|
||||
pitch_floor=f0_min,
|
||||
pitch_ceiling=1100,
|
||||
)
|
||||
assert np.abs(s.t1 - 1.5 / f0_min) < 0.001
|
||||
f0 = s.selected_array["frequency"]
|
||||
if len(f0) < p_len:
|
||||
f0 = np.pad(f0, (0, p_len - len(f0)))
|
||||
f0 = f0[:p_len]
|
||||
f0 *= pow(2, f0_up_key / 12)
|
||||
return self.get_f0_post(f0)
|
||||
if n_cpu == 1:
|
||||
f0, t = pyworld.harvest(
|
||||
x.astype(np.double),
|
||||
fs=16000,
|
||||
f0_ceil=1100,
|
||||
f0_floor=50,
|
||||
frame_period=10,
|
||||
)
|
||||
f0 = signal.medfilt(f0, 3)
|
||||
f0 *= pow(2, f0_up_key / 12)
|
||||
return self.get_f0_post(f0)
|
||||
f0bak = np.zeros(x.shape[0] // 160 + 1, dtype=np.float64)
|
||||
length = len(x)
|
||||
part_length = 160 * ((length // 160 - 1) // n_cpu + 1)
|
||||
n_cpu = (length // 160 - 1) // (part_length // 160) + 1
|
||||
ts = ttime()
|
||||
res_f0 = mm.dict()
|
||||
for idx in range(n_cpu):
|
||||
tail = part_length * (idx + 1) + 320
|
||||
if idx == 0:
|
||||
self.inp_q.put((idx, x[:tail], res_f0, n_cpu, ts))
|
||||
else:
|
||||
self.inp_q.put(
|
||||
(idx, x[part_length * idx - 320 : tail], res_f0, n_cpu, ts)
|
||||
)
|
||||
while 1:
|
||||
res_ts = self.opt_q.get()
|
||||
if res_ts == ts:
|
||||
break
|
||||
f0s = [i[1] for i in sorted(res_f0.items(), key=lambda x: x[0])]
|
||||
for idx, f0 in enumerate(f0s):
|
||||
if idx == 0:
|
||||
f0 = f0[:-3]
|
||||
elif idx != n_cpu - 1:
|
||||
f0 = f0[2:-3]
|
||||
else:
|
||||
f0 = f0[2:]
|
||||
f0bak[part_length * idx // 160 : part_length * idx // 160 + f0.shape[0]] = (
|
||||
f0
|
||||
)
|
||||
f0bak = signal.medfilt(f0bak, 3)
|
||||
f0bak *= pow(2, f0_up_key / 12)
|
||||
return self.get_f0_post(f0bak)
|
||||
|
||||
def get_f0_crepe(self, x, f0_up_key):
|
||||
if "privateuseone" in str(
|
||||
self.device
|
||||
): ###不支持dml，cpu又太慢用不成，拿fcpe顶替
|
||||
return self.get_f0(x, f0_up_key, 1, "fcpe")
|
||||
# printt("using crepe,device:%s"%self.device)
|
||||
f0, pd = torchcrepe.predict(
|
||||
x.unsqueeze(0).float(),
|
||||
16000,
|
||||
160,
|
||||
self.f0_min,
|
||||
self.f0_max,
|
||||
"full",
|
||||
batch_size=512,
|
||||
# device=self.device if self.device.type!="privateuseone" else "cpu",###crepe不用半精度全部是全精度所以不愁###cpu延迟高到没法用
|
||||
device=self.device,
|
||||
return_periodicity=True,
|
||||
)
|
||||
pd = torchcrepe.filter.median(pd, 3)
|
||||
f0 = torchcrepe.filter.mean(f0, 3)
|
||||
f0[pd < 0.1] = 0
|
||||
f0 *= pow(2, f0_up_key / 12)
|
||||
return self.get_f0_post(f0)
|
||||
|
||||
def get_f0_rmvpe(self, x, f0_up_key):
|
||||
if hasattr(self, "model_rmvpe") == False:
|
||||
from infer.lib.rmvpe import RMVPE
|
||||
|
||||
printt("Loading rmvpe model")
|
||||
self.model_rmvpe = RMVPE(
|
||||
"assets/rmvpe/rmvpe.pt",
|
||||
is_half=self.is_half,
|
||||
device=self.device,
|
||||
use_jit=self.config.use_jit,
|
||||
)
|
||||
f0 = self.model_rmvpe.infer_from_audio(x, thred=0.03)
|
||||
f0 *= pow(2, f0_up_key / 12)
|
||||
return self.get_f0_post(f0)
|
||||
|
||||
def get_f0_fcpe(self, x, f0_up_key):
|
||||
if hasattr(self, "model_fcpe") == False:
|
||||
from torchfcpe import spawn_bundled_infer_model
|
||||
|
||||
printt("Loading fcpe model")
|
||||
if "privateuseone" in str(self.device):
|
||||
self.device_fcpe = "cpu"
|
||||
else:
|
||||
self.device_fcpe = self.device
|
||||
self.model_fcpe = spawn_bundled_infer_model(self.device_fcpe)
|
||||
f0 = self.model_fcpe.infer(
|
||||
x.to(self.device_fcpe).unsqueeze(0).float(),
|
||||
sr=16000,
|
||||
decoder_mode="local_argmax",
|
||||
threshold=0.006,
|
||||
)
|
||||
f0 *= pow(2, f0_up_key / 12)
|
||||
return self.get_f0_post(f0)
|
||||
|
||||
def infer(
|
||||
self,
|
||||
input_wav: torch.Tensor,
|
||||
block_frame_16k,
|
||||
skip_head,
|
||||
return_length,
|
||||
f0method,
|
||||
) -> np.ndarray:
|
||||
t1 = ttime()
|
||||
with torch.no_grad():
|
||||
if self.config.is_half:
|
||||
feats = input_wav.half().view(1, -1)
|
||||
else:
|
||||
feats = input_wav.float().view(1, -1)
|
||||
padding_mask = torch.BoolTensor(feats.shape).to(self.device).fill_(False)
|
||||
inputs = {
|
||||
"source": feats,
|
||||
"padding_mask": padding_mask,
|
||||
"output_layer": 9 if self.version == "v1" else 12,
|
||||
}
|
||||
logits = self.model.extract_features(**inputs)
|
||||
feats = (
|
||||
self.model.final_proj(logits[0]) if self.version == "v1" else logits[0]
|
||||
)
|
||||
feats = torch.cat((feats, feats[:, -1:, :]), 1)
|
||||
t2 = ttime()
|
||||
try:
|
||||
if hasattr(self, "index") and self.index_rate != 0:
|
||||
npy = feats[0][skip_head // 2 :].cpu().numpy().astype("float32")
|
||||
score, ix = self.index.search(npy, k=8)
|
||||
if (ix >= 0).all():
|
||||
weight = np.square(1 / score)
|
||||
weight /= weight.sum(axis=1, keepdims=True)
|
||||
npy = np.sum(
|
||||
self.big_npy[ix] * np.expand_dims(weight, axis=2), axis=1
|
||||
)
|
||||
if self.config.is_half:
|
||||
npy = npy.astype("float16")
|
||||
feats[0][skip_head // 2 :] = (
|
||||
torch.from_numpy(npy).unsqueeze(0).to(self.device)
|
||||
* self.index_rate
|
||||
+ (1 - self.index_rate) * feats[0][skip_head // 2 :]
|
||||
)
|
||||
else:
|
||||
printt(
|
||||
"Invalid index. You MUST use added_xxxx.index but not trained_xxxx.index!"
|
||||
)
|
||||
else:
|
||||
printt("Index search FAILED or disabled")
|
||||
except:
|
||||
traceback.print_exc()
|
||||
printt("Index search FAILED")
|
||||
t3 = ttime()
|
||||
p_len = input_wav.shape[0] // 160
|
||||
if self.if_f0 == 1:
|
||||
f0_extractor_frame = block_frame_16k + 800
|
||||
if f0method == "rmvpe":
|
||||
f0_extractor_frame = 5120 * ((f0_extractor_frame - 1) // 5120 + 1) - 160
|
||||
pitch, pitchf = self.get_f0(
|
||||
input_wav[-f0_extractor_frame:], self.f0_up_key, self.n_cpu, f0method
|
||||
)
|
||||
shift = block_frame_16k // 160
|
||||
self.cache_pitch[:-shift] = self.cache_pitch[shift:].clone()
|
||||
self.cache_pitchf[:-shift] = self.cache_pitchf[shift:].clone()
|
||||
self.cache_pitch[4 - pitch.shape[0] :] = pitch[3:-1]
|
||||
self.cache_pitchf[4 - pitch.shape[0] :] = pitchf[3:-1]
|
||||
cache_pitch = self.cache_pitch[None, -p_len:]
|
||||
cache_pitchf = self.cache_pitchf[None, -p_len:]
|
||||
t4 = ttime()
|
||||
feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
|
||||
feats = feats[:, :p_len, :]
|
||||
p_len = torch.LongTensor([p_len]).to(self.device)
|
||||
sid = torch.LongTensor([0]).to(self.device)
|
||||
skip_head = torch.LongTensor([skip_head])
|
||||
return_length = torch.LongTensor([return_length])
|
||||
with torch.no_grad():
|
||||
if self.if_f0 == 1:
|
||||
infered_audio, _, _ = self.net_g.infer(
|
||||
feats,
|
||||
p_len,
|
||||
cache_pitch,
|
||||
cache_pitchf,
|
||||
sid,
|
||||
skip_head,
|
||||
return_length,
|
||||
)
|
||||
else:
|
||||
infered_audio, _, _ = self.net_g.infer(
|
||||
feats, p_len, sid, skip_head, return_length
|
||||
)
|
||||
t5 = ttime()
|
||||
printt(
|
||||
"Spent time: fea = %.3fs, index = %.3fs, f0 = %.3fs, model = %.3fs",
|
||||
t2 - t1,
|
||||
t3 - t2,
|
||||
t4 - t3,
|
||||
t5 - t4,
|
||||
)
|
||||
return infered_audio.squeeze().float()
|
||||
@@ -1,13 +0,0 @@
|
||||
"""
|
||||
TorchGating is a PyTorch-based implementation of Spectral Gating
|
||||
================================================
|
||||
Author: Asaf Zorea
|
||||
|
||||
Contents
|
||||
--------
|
||||
torchgate imports all the functions from PyTorch, and in addition provides:
|
||||
TorchGating --- A PyTorch module that applies a spectral gate to an input signal
|
||||
|
||||
"""
|
||||
|
||||
from .torchgate import TorchGate
|
||||
@@ -1,280 +0,0 @@
|
||||
import torch
|
||||
from infer.lib.rmvpe import STFT
|
||||
from torch.nn.functional import conv1d, conv2d
|
||||
from typing import Union, Optional
|
||||
from .utils import linspace, temperature_sigmoid, amp_to_db
|
||||
|
||||
|
||||
class TorchGate(torch.nn.Module):
|
||||
"""
|
||||
A PyTorch module that applies a spectral gate to an input signal.
|
||||
|
||||
Arguments:
|
||||
sr {int} -- Sample rate of the input signal.
|
||||
nonstationary {bool} -- Whether to use non-stationary or stationary masking (default: {False}).
|
||||
n_std_thresh_stationary {float} -- Number of standard deviations above mean to threshold noise for
|
||||
stationary masking (default: {1.5}).
|
||||
n_thresh_nonstationary {float} -- Number of multiplies above smoothed magnitude spectrogram. for
|
||||
non-stationary masking (default: {1.3}).
|
||||
temp_coeff_nonstationary {float} -- Temperature coefficient for non-stationary masking (default: {0.1}).
|
||||
n_movemean_nonstationary {int} -- Number of samples for moving average smoothing in non-stationary masking
|
||||
(default: {20}).
|
||||
prop_decrease {float} -- Proportion to decrease signal by where the mask is zero (default: {1.0}).
|
||||
n_fft {int} -- Size of FFT for STFT (default: {1024}).
|
||||
win_length {[int]} -- Window length for STFT. If None, defaults to `n_fft` (default: {None}).
|
||||
hop_length {[int]} -- Hop length for STFT. If None, defaults to `win_length` // 4 (default: {None}).
|
||||
freq_mask_smooth_hz {float} -- Frequency smoothing width for mask (in Hz). If None, no smoothing is applied
|
||||
(default: {500}).
|
||||
time_mask_smooth_ms {float} -- Time smoothing width for mask (in ms). If None, no smoothing is applied
|
||||
(default: {50}).
|
||||
"""
|
||||
|
||||
@torch.no_grad()
|
||||
def __init__(
|
||||
self,
|
||||
sr: int,
|
||||
nonstationary: bool = False,
|
||||
n_std_thresh_stationary: float = 1.5,
|
||||
n_thresh_nonstationary: float = 1.3,
|
||||
temp_coeff_nonstationary: float = 0.1,
|
||||
n_movemean_nonstationary: int = 20,
|
||||
prop_decrease: float = 1.0,
|
||||
n_fft: int = 1024,
|
||||
win_length: bool = None,
|
||||
hop_length: int = None,
|
||||
freq_mask_smooth_hz: float = 500,
|
||||
time_mask_smooth_ms: float = 50,
|
||||
):
|
||||
super().__init__()
|
||||
|
||||
# General Params
|
||||
self.sr = sr
|
||||
self.nonstationary = nonstationary
|
||||
assert 0.0 <= prop_decrease <= 1.0
|
||||
self.prop_decrease = prop_decrease
|
||||
|
||||
# STFT Params
|
||||
self.n_fft = n_fft
|
||||
self.win_length = self.n_fft if win_length is None else win_length
|
||||
self.hop_length = self.win_length // 4 if hop_length is None else hop_length
|
||||
|
||||
# Stationary Params
|
||||
self.n_std_thresh_stationary = n_std_thresh_stationary
|
||||
|
||||
# Non-Stationary Params
|
||||
self.temp_coeff_nonstationary = temp_coeff_nonstationary
|
||||
self.n_movemean_nonstationary = n_movemean_nonstationary
|
||||
self.n_thresh_nonstationary = n_thresh_nonstationary
|
||||
|
||||
# Smooth Mask Params
|
||||
self.freq_mask_smooth_hz = freq_mask_smooth_hz
|
||||
self.time_mask_smooth_ms = time_mask_smooth_ms
|
||||
self.register_buffer("smoothing_filter", self._generate_mask_smoothing_filter())
|
||||
|
||||
@torch.no_grad()
|
||||
def _generate_mask_smoothing_filter(self) -> Union[torch.Tensor, None]:
|
||||
"""
|
||||
A PyTorch module that applies a spectral gate to an input signal using the STFT.
|
||||
|
||||
Returns:
|
||||
smoothing_filter (torch.Tensor): a 2D tensor representing the smoothing filter,
|
||||
with shape (n_grad_freq, n_grad_time), where n_grad_freq is the number of frequency
|
||||
bins to smooth and n_grad_time is the number of time frames to smooth.
|
||||
If both self.freq_mask_smooth_hz and self.time_mask_smooth_ms are None, returns None.
|
||||
"""
|
||||
if self.freq_mask_smooth_hz is None and self.time_mask_smooth_ms is None:
|
||||
return None
|
||||
|
||||
n_grad_freq = (
|
||||
1
|
||||
if self.freq_mask_smooth_hz is None
|
||||
else int(self.freq_mask_smooth_hz / (self.sr / (self.n_fft / 2)))
|
||||
)
|
||||
if n_grad_freq < 1:
|
||||
raise ValueError(
|
||||
f"freq_mask_smooth_hz needs to be at least {int((self.sr / (self._n_fft / 2)))} Hz"
|
||||
)
|
||||
|
||||
n_grad_time = (
|
||||
1
|
||||
if self.time_mask_smooth_ms is None
|
||||
else int(self.time_mask_smooth_ms / ((self.hop_length / self.sr) * 1000))
|
||||
)
|
||||
if n_grad_time < 1:
|
||||
raise ValueError(
|
||||
f"time_mask_smooth_ms needs to be at least {int((self.hop_length / self.sr) * 1000)} ms"
|
||||
)
|
||||
|
||||
if n_grad_time == 1 and n_grad_freq == 1:
|
||||
return None
|
||||
|
||||
v_f = torch.cat(
|
||||
[
|
||||
linspace(0, 1, n_grad_freq + 1, endpoint=False),
|
||||
linspace(1, 0, n_grad_freq + 2),
|
||||
]
|
||||
)[1:-1]
|
||||
v_t = torch.cat(
|
||||
[
|
||||
linspace(0, 1, n_grad_time + 1, endpoint=False),
|
||||
linspace(1, 0, n_grad_time + 2),
|
||||
]
|
||||
)[1:-1]
|
||||
smoothing_filter = torch.outer(v_f, v_t).unsqueeze(0).unsqueeze(0)
|
||||
|
||||
return smoothing_filter / smoothing_filter.sum()
|
||||
|
||||
@torch.no_grad()
|
||||
def _stationary_mask(
|
||||
self, X_db: torch.Tensor, xn: Optional[torch.Tensor] = None
|
||||
) -> torch.Tensor:
|
||||
"""
|
||||
Computes a stationary binary mask to filter out noise in a log-magnitude spectrogram.
|
||||
|
||||
Arguments:
|
||||
X_db (torch.Tensor): 2D tensor of shape (frames, freq_bins) containing the log-magnitude spectrogram.
|
||||
xn (torch.Tensor): 1D tensor containing the audio signal corresponding to X_db.
|
||||
|
||||
Returns:
|
||||
sig_mask (torch.Tensor): Binary mask of the same shape as X_db, where values greater than the threshold
|
||||
are set to 1, and the rest are set to 0.
|
||||
"""
|
||||
if xn is not None:
|
||||
if "privateuseone" in str(xn.device):
|
||||
if not hasattr(self, "stft"):
|
||||
self.stft = STFT(
|
||||
filter_length=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
window="hann",
|
||||
).to(xn.device)
|
||||
XN = self.stft.transform(xn)
|
||||
else:
|
||||
XN = torch.stft(
|
||||
xn,
|
||||
n_fft=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
return_complex=True,
|
||||
pad_mode="constant",
|
||||
center=True,
|
||||
window=torch.hann_window(self.win_length).to(xn.device),
|
||||
)
|
||||
XN_db = amp_to_db(XN).to(dtype=X_db.dtype)
|
||||
else:
|
||||
XN_db = X_db
|
||||
|
||||
# calculate mean and standard deviation along the frequency axis
|
||||
std_freq_noise, mean_freq_noise = torch.std_mean(XN_db, dim=-1)
|
||||
|
||||
# compute noise threshold
|
||||
noise_thresh = mean_freq_noise + std_freq_noise * self.n_std_thresh_stationary
|
||||
|
||||
# create binary mask by thresholding the spectrogram
|
||||
sig_mask = X_db > noise_thresh.unsqueeze(2)
|
||||
return sig_mask
|
||||
|
||||
@torch.no_grad()
|
||||
def _nonstationary_mask(self, X_abs: torch.Tensor) -> torch.Tensor:
|
||||
"""
|
||||
Computes a non-stationary binary mask to filter out noise in a log-magnitude spectrogram.
|
||||
|
||||
Arguments:
|
||||
X_abs (torch.Tensor): 2D tensor of shape (frames, freq_bins) containing the magnitude spectrogram.
|
||||
|
||||
Returns:
|
||||
sig_mask (torch.Tensor): Binary mask of the same shape as X_abs, where values greater than the threshold
|
||||
are set to 1, and the rest are set to 0.
|
||||
"""
|
||||
X_smoothed = (
|
||||
conv1d(
|
||||
X_abs.reshape(-1, 1, X_abs.shape[-1]),
|
||||
torch.ones(
|
||||
self.n_movemean_nonstationary,
|
||||
dtype=X_abs.dtype,
|
||||
device=X_abs.device,
|
||||
).view(1, 1, -1),
|
||||
padding="same",
|
||||
).view(X_abs.shape)
|
||||
/ self.n_movemean_nonstationary
|
||||
)
|
||||
|
||||
# Compute slowness ratio and apply temperature sigmoid
|
||||
slowness_ratio = (X_abs - X_smoothed) / (X_smoothed + 1e-6)
|
||||
sig_mask = temperature_sigmoid(
|
||||
slowness_ratio, self.n_thresh_nonstationary, self.temp_coeff_nonstationary
|
||||
)
|
||||
|
||||
return sig_mask
|
||||
|
||||
def forward(
|
||||
self, x: torch.Tensor, xn: Optional[torch.Tensor] = None
|
||||
) -> torch.Tensor:
|
||||
"""
|
||||
Apply the proposed algorithm to the input signal.
|
||||
|
||||
Arguments:
|
||||
x (torch.Tensor): The input audio signal, with shape (batch_size, signal_length).
|
||||
xn (Optional[torch.Tensor]): The noise signal used for stationary noise reduction. If `None`, the input
|
||||
signal is used as the noise signal. Default: `None`.
|
||||
|
||||
Returns:
|
||||
torch.Tensor: The denoised audio signal, with the same shape as the input signal.
|
||||
"""
|
||||
|
||||
# Compute short-time Fourier transform (STFT)
|
||||
if "privateuseone" in str(x.device):
|
||||
if not hasattr(self, "stft"):
|
||||
self.stft = STFT(
|
||||
filter_length=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
window="hann",
|
||||
).to(x.device)
|
||||
X, phase = self.stft.transform(x, return_phase=True)
|
||||
else:
|
||||
X = torch.stft(
|
||||
x,
|
||||
n_fft=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
return_complex=True,
|
||||
pad_mode="constant",
|
||||
center=True,
|
||||
window=torch.hann_window(self.win_length).to(x.device),
|
||||
)
|
||||
|
||||
# Compute signal mask based on stationary or nonstationary assumptions
|
||||
if self.nonstationary:
|
||||
sig_mask = self._nonstationary_mask(X.abs())
|
||||
else:
|
||||
sig_mask = self._stationary_mask(amp_to_db(X), xn)
|
||||
|
||||
# Propagate decrease in signal power
|
||||
sig_mask = self.prop_decrease * (sig_mask.float() - 1.0) + 1.0
|
||||
|
||||
# Smooth signal mask with 2D convolution
|
||||
if self.smoothing_filter is not None:
|
||||
sig_mask = conv2d(
|
||||
sig_mask.unsqueeze(1),
|
||||
self.smoothing_filter.to(sig_mask.dtype),
|
||||
padding="same",
|
||||
)
|
||||
|
||||
# Apply signal mask to STFT magnitude and phase components
|
||||
Y = X * sig_mask.squeeze(1)
|
||||
|
||||
# Inverse STFT to obtain time-domain signal
|
||||
if "privateuseone" in str(Y.device):
|
||||
y = self.stft.inverse(Y, phase)
|
||||
else:
|
||||
y = torch.istft(
|
||||
Y,
|
||||
n_fft=self.n_fft,
|
||||
hop_length=self.hop_length,
|
||||
win_length=self.win_length,
|
||||
center=True,
|
||||
window=torch.hann_window(self.win_length).to(Y.device),
|
||||
)
|
||||
|
||||
return y.to(dtype=x.dtype)
|
||||
@@ -1,70 +0,0 @@
|
||||
import torch
|
||||
from torch.types import Number
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def amp_to_db(
|
||||
x: torch.Tensor, eps=torch.finfo(torch.float64).eps, top_db=40
|
||||
) -> torch.Tensor:
|
||||
"""
|
||||
Convert the input tensor from amplitude to decibel scale.
|
||||
|
||||
Arguments:
|
||||
x {[torch.Tensor]} -- [Input tensor.]
|
||||
|
||||
Keyword Arguments:
|
||||
eps {[float]} -- [Small value to avoid numerical instability.]
|
||||
(default: {torch.finfo(torch.float64).eps})
|
||||
top_db {[float]} -- [threshold the output at ``top_db`` below the peak]
|
||||
` (default: {40})
|
||||
|
||||
Returns:
|
||||
[torch.Tensor] -- [Output tensor in decibel scale.]
|
||||
"""
|
||||
x_db = 20 * torch.log10(x.abs() + eps)
|
||||
return torch.max(x_db, (x_db.max(-1).values - top_db).unsqueeze(-1))
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def temperature_sigmoid(x: torch.Tensor, x0: float, temp_coeff: float) -> torch.Tensor:
|
||||
"""
|
||||
Apply a sigmoid function with temperature scaling.
|
||||
|
||||
Arguments:
|
||||
x {[torch.Tensor]} -- [Input tensor.]
|
||||
x0 {[float]} -- [Parameter that controls the threshold of the sigmoid.]
|
||||
temp_coeff {[float]} -- [Parameter that controls the slope of the sigmoid.]
|
||||
|
||||
Returns:
|
||||
[torch.Tensor] -- [Output tensor after applying the sigmoid with temperature scaling.]
|
||||
"""
|
||||
return torch.sigmoid((x - x0) / temp_coeff)
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def linspace(
|
||||
start: Number, stop: Number, num: int = 50, endpoint: bool = True, **kwargs
|
||||
) -> torch.Tensor:
|
||||
"""
|
||||
Generate a linearly spaced 1-D tensor.
|
||||
|
||||
Arguments:
|
||||
start {[Number]} -- [The starting value of the sequence.]
|
||||
stop {[Number]} -- [The end value of the sequence, unless `endpoint` is set to False.
|
||||
In that case, the sequence consists of all but the last of ``num + 1``
|
||||
evenly spaced samples, so that `stop` is excluded. Note that the step
|
||||
size changes when `endpoint` is False.]
|
||||
|
||||
Keyword Arguments:
|
||||
num {[int]} -- [Number of samples to generate. Default is 50. Must be non-negative.]
|
||||
endpoint {[bool]} -- [If True, `stop` is the last sample. Otherwise, it is not included.
|
||||
Default is True.]
|
||||
**kwargs -- [Additional arguments to be passed to the underlying PyTorch `linspace` function.]
|
||||
|
||||
Returns:
|
||||
[torch.Tensor] -- [1-D tensor of `num` equally spaced samples from `start` to `stop`.]
|
||||
"""
|
||||
if endpoint:
|
||||
return torch.linspace(start, stop, num, **kwargs)
|
||||
else:
|
||||
return torch.linspace(start, stop, num + 1, **kwargs)[:-1]
|
||||
Reference in New Issue
Block a user