update colab notebooks (#1023)

Retrieval_based_Voice_Conversion_WebUI.ipynb

@@ -1,30 +1,22 @@
 {
- "nbformat": 4,
- "nbformat_minor": 0,
- "metadata": {
-  "colab": {
-   "private_outputs": true,
-   "provenance": []
-  },
-  "kernelspec": {
-   "name": "python3",
-   "display_name": "Python 3"
-  },
-  "language_info": {
-   "name": "python"
-  },
-  "accelerator": "GPU",
-  "gpuClass": "standard"
- },
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)"
+    "# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
-   ],
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
    "metadata": {
     "id": "ZFFCx5J80SGa"
-   }
+   },
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)"
+   ]
   },
   {
    "cell_type": "code",
@@ -40,60 +32,80 @@
   },
   {
    "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-get -y install build-essential python3-dev ffmpeg\n",
     "!pip3 install --upgrade setuptools wheel\n",
     "!pip3 install --upgrade pip\n",
     "!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"
-   ],
+   ]
-   "metadata": {
-    "id": "wjddIFr1oS3W"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ge_97mfpgqTm"
+   },
+   "outputs": [],
    "source": [
     "# @title 克隆仓库\n",
     "\n",
     "!git clone --depth=1 -b stable https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI\n",
     "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
     "!mkdir -p pretrained uvr5_weights"
-   ],
+   ]
-   "metadata": {
-    "id": "ge_97mfpgqTm"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "code",
-   "source": [
+   "execution_count": null,
-    "# @title 更新仓库（一般无需执行）\n",
-    "!git pull"
-   ],
    "metadata": {
     "id": "BLDEZADkvlw1"
    },
-   "execution_count": null,
+   "outputs": [],
-   "outputs": []
+   "source": [
+    "# @title 更新仓库（一般无需执行）\n",
+    "!git pull"
+   ]
   },
   {
    "cell_type": "code",
-   "source": [
+   "execution_count": null,
-    "# @title 安装aria2\n",
-    "!apt -y install -qq aria2"
-   ],
    "metadata": {
     "id": "pqE0PrnuRqI2"
    },
-   "execution_count": null,
+   "outputs": [],
-   "outputs": []
+   "source": [
+    "# @title 安装aria2\n",
+    "!apt -y install -qq aria2"
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "UG3XpUwEomUz"
+   },
+   "outputs": [],
    "source": [
     "# @title 下载底模\n",
     "!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\n",
@@ -108,55 +120,50 @@
     "!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\n",
     "!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\n",
     "!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"
-   ],
+   ]
-   "metadata": {
-    "id": "UG3XpUwEomUz"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "HugjmZqZRuiF"
+   },
+   "outputs": [],
    "source": [
     "# @title 下载人声分离模型\n",
     "!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\n",
     "!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"
-   ],
+   ]
-   "metadata": {
-    "id": "HugjmZqZRuiF"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "code",
-   "source": [
+   "execution_count": null,
-    "# @title 下载hubert_base\n",
-    "!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"
-   ],
    "metadata": {
     "id": "2RCaT9FTR0ej"
    },
-   "execution_count": null,
+   "outputs": [],
-   "outputs": []
-  },
-  {
-   "cell_type": "code",
    "source": [
-    "# @title 挂载谷歌云盘\n",
+    "# @title 下载hubert_base\n",
-    "\n",
+    "!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"
-    "from google.colab import drive\n",
+   ]
-    "\n",
-    "drive.mount(\"/content/drive\")"
-   ],
-   "metadata": {
-    "id": "jwu07JgqoFON"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# @title #下载rmvpe模型\n",
+    "!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"
+   ]
+  },
+  {
+   "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",
@@ -167,43 +174,43 @@
     "\n",
     "!mkdir -p /content/dataset\n",
     "!unzip -d /content/dataset -B {DATASET}"
-   ],
+   ]
-   "metadata": {
-    "id": "Mwk7Q0Loqzjx"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "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/*.*~*"
-   ],
+   ]
-   "metadata": {
-    "id": "PDlFxWHWEynD"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "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"
-   ],
+   ]
-   "metadata": {
-    "id": "7vh6vphDwO0b"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "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",
@@ -219,15 +226,15 @@
     "!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"
-   ],
+   ]
-   "metadata": {
-    "id": "FgJuNeAwx5Y_"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "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",
@@ -244,15 +251,15 @@
     "!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"
-   ],
+   ]
-   "metadata": {
-    "id": "OVQoLQJXS7WX"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "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",
@@ -263,15 +270,15 @@
     "THREADCOUNT = 8  # @param {type:\"integer\"}\n",
     "\n",
     "!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True"
-   ],
+   ]
-   "metadata": {
-    "id": "ZKAyuKb9J6dz"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "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",
@@ -284,15 +291,15 @@
     "!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
     "\n",
     "!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME}"
-   ],
+   ]
-   "metadata": {
-    "id": "CrxJqzAUKmPJ"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "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",
@@ -313,15 +320,15 @@
     "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}"
-   ],
+   ]
-   "metadata": {
-    "id": "IMLPLKOaKj58"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "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",
@@ -343,15 +350,15 @@
     "\n",
     "!echo \"删除完成\"\n",
     "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
-   ],
+   ]
-   "metadata": {
-    "id": "haYA81hySuDl"
-   },
-   "execution_count": null,
-   "outputs": []
   },
   {
    "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",
@@ -373,12 +380,24 @@
     "\n",
     "!echo \"删除完成\"\n",
     "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
-   ],
+   ]
-   "metadata": {
-    "id": "QhSiPTVPoIRh"
-   },
-   "execution_count": null,
-   "outputs": []
   }
- ]
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "private_outputs": true,
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
 }

Retrieval_based_Voice_Conversion_WebUI_v2.ipynb

@@ -1,5 +1,13 @@
 {
  "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -18,10 +26,25 @@
    },
    "outputs": [],
    "source": [
-    "# @title 查看显卡\n",
+    "# @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,
@@ -30,7 +53,7 @@
    },
    "outputs": [],
    "source": [
-    "# @title 安装依赖\n",
+    "# @title #安装依赖\n",
     "!apt-get -y install build-essential python3-dev ffmpeg\n",
     "!pip3 install --upgrade setuptools wheel\n",
     "!pip3 install --upgrade pip\n",
@@ -45,7 +68,7 @@
    },
    "outputs": [],
    "source": [
-    "# @title 克隆仓库\n",
+    "# @title #克隆仓库\n",
     "\n",
     "!mkdir Retrieval-based-Voice-Conversion-WebUI\n",
     "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
@@ -63,7 +86,7 @@
    },
    "outputs": [],
    "source": [
-    "# @title 更新仓库（一般无需执行）\n",
+    "# @title #更新仓库（一般无需执行）\n",
     "!git pull"
    ]
   },
@@ -75,7 +98,7 @@
    },
    "outputs": [],
    "source": [
-    "# @title 安装aria2\n",
+    "# @title #安装aria2\n",
     "!apt -y install -qq aria2"
    ]
   },
@@ -126,7 +149,7 @@
    },
    "outputs": [],
    "source": [
-    "# @title 下载人声分离模型\n",
+    "# @title #下载人声分离模型\n",
     "!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\n",
     "!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"
    ]
@@ -139,23 +162,18 @@
    },
    "outputs": [],
    "source": [
-    "# @title 下载hubert_base\n",
+    "# @title #下载hubert_base\n",
     "!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"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
+   "metadata": {},
-    "id": "jwu07JgqoFON"
-   },
    "outputs": [],
    "source": [
-    "# @title 挂载谷歌云盘\n",
+    "# @title #下载rmvpe模型\n",
-    "\n",
+    "!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"
-    "from google.colab import drive\n",
-    "\n",
-    "drive.mount(\"/content/drive\")"
    ]
   },
   {
@@ -166,7 +184,7 @@
    },
    "outputs": [],
    "source": [
-    "# @title 从谷歌云盘加载打包好的数据集到/content/dataset\n",
+    "# @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 = (\n",
@@ -185,7 +203,7 @@
    },
    "outputs": [],
    "source": [
-    "# @title 重命名数据集中的重名文件\n",
+    "# @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/*.*~*"
    ]
@@ -198,7 +216,7 @@
    },
    "outputs": [],
    "source": [
-    "# @title 启动web\n",
+    "# @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",
@@ -213,12 +231,12 @@
    },
    "outputs": [],
    "source": [
-    "# @title 手动将训练后的模型文件备份到谷歌云盘\n",
+    "# @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",
+    "# @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",
+    "# @markdown #模型名\n",
     "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
-    "# @markdown 模型epoch\n",
+    "# @markdown #模型epoch\n",
     "MODELEPOCH = 9600  # @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",