ChazzyG/Retrieval-based-Voice-Conversion-WebUI
0
1{2 "nbformat": 4,3 "nbformat_minor": 0,4 "metadata": {5 "colab": {6 "private_outputs": true,7 "provenance": []8 },9 "kernelspec": {10 "name": "python3",11 "display_name": "Python 3"12 },13 "language_info": {14 "name": "python"15 },16 "accelerator": "GPU",17 "gpuClass": "standard"18 },19 "cells": [20 {21 "cell_type": "markdown",22 "source": [23 "[](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)"24 ],25 "metadata": {26 "id": "ZFFCx5J80SGa"27 }28 },29 {30 "cell_type": "code",31 "execution_count": null,32 "metadata": {33 "id": "GmFP6bN9dvOq"34 },35 "outputs": [],36 "source": [37 "#@title 查看显卡\n",38 "!nvidia-smi"39 ]40 },41 {42 "cell_type": "code",43 "source": [44 "#@title 安装依赖\n",45 "!apt-get -y install build-essential python3-dev ffmpeg\n",46 "!pip3 install --upgrade setuptools wheel\n",47 "!pip3 install --upgrade pip\n",48 "!pip3 install faiss-gpu fairseq gradio ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2"49 ],50 "metadata": {51 "id": "wjddIFr1oS3W"52 },53 "execution_count": null,54 "outputs": []55 },56 {57 "cell_type": "code",58 "source": [59 "#@title 克隆仓库\n",60 "\n",61 "!git clone --depth=1 -b stable https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI\n",62 "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",63 "!mkdir -p pretrained uvr5_weights"64 ],65 "metadata": {66 "id": "ge_97mfpgqTm"67 },68 "execution_count": null,69 "outputs": []70 },71 {72 "cell_type": "code",73 "source": [74 "#@title 更新仓库（一般无需执行）\n",75 "!git pull"76 ],77 "metadata": {78 "id": "BLDEZADkvlw1"79 },80 "execution_count": null,81 "outputs": []82 },83 {84 "cell_type": "code",85 "source": [86 "#@title 安装aria2\n",87 "!apt -y install -qq aria2"88 ],89 "metadata": {90 "id": "pqE0PrnuRqI2"91 },92 "execution_count": null,93 "outputs": []94 },95 {96 "cell_type": "code",97 "source": [98 "#@title 下载底模\n",99 "!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",100 "!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\n",101 "!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\n",102 "!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\n",103 "!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\n",104 "!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\n",105 "!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\n",106 "!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\n",107 "!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\n",108 "!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",109 "!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",110 "!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"111 ],112 "metadata": {113 "id": "UG3XpUwEomUz"114 },115 "execution_count": null,116 "outputs": []117 },118 {119 "cell_type": "code",120 "source": [121 "#@title 下载人声分离模型\n",122 "!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",123 "!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"124 ],125 "metadata": {126 "id": "HugjmZqZRuiF"127 },128 "execution_count": null,129 "outputs": []130 },131 {132 "cell_type": "code",133 "source": [134 "#@title 下载hubert_base\n",135 "!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"136 ],137 "metadata": {138 "id": "2RCaT9FTR0ej"139 },140 "execution_count": null,141 "outputs": []142 },143 {144 "cell_type": "code",145 "source": [146 "#@title 挂载谷歌云盘\n",147 "\n",148 "from google.colab import drive\n",149 "drive.mount('/content/drive')"150 ],151 "metadata": {152 "id": "jwu07JgqoFON"153 },154 "execution_count": null,155 "outputs": []156 },157 {158 "cell_type": "code",159 "source": [160 "#@title 从谷歌云盘加载打包好的数据集到/content/dataset\n",161 "\n",162 "#@markdown 数据集位置\n",163 "DATASET = \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\" #@param {type:\"string\"}\n",164 "\n",165 "!mkdir -p /content/dataset\n",166 "!unzip -d /content/dataset -B {DATASET}"167 ],168 "metadata": {169 "id": "Mwk7Q0Loqzjx"170 },171 "execution_count": null,172 "outputs": []173 },174 {175 "cell_type": "code",176 "source": [177 "#@title 重命名数据集中的重名文件\n",178 "!ls -a /content/dataset/\n",179 "!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"180 ],181 "metadata": {182 "id": "PDlFxWHWEynD"183 },184 "execution_count": null,185 "outputs": []186 },187 {188 "cell_type": "code",189 "source": [190 "#@title 启动web\n",191 "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",192 "# %load_ext tensorboard\n",193 "# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",194 "!python3 infer-web.py --colab --pycmd python3"195 ],196 "metadata": {197 "id": "7vh6vphDwO0b"198 },199 "execution_count": null,200 "outputs": []201 },202 {203 "cell_type": "code",204 "source": [205 "#@title 手动将训练后的模型文件备份到谷歌云盘\n",206 "#@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",207 "\n",208 "#@markdown 模型名\n",209 "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",210 "#@markdown 模型epoch\n",211 "MODELEPOCH = 9600 #@param {type:\"integer\"}\n",212 "\n",213 "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",214 "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",215 "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",216 "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",217 "\n",218 "!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"219 ],220 "metadata": {221 "id": "FgJuNeAwx5Y_"222 },223 "execution_count": null,224 "outputs": []225 },226 {227 "cell_type": "code",228 "source": [229 "#@title 从谷歌云盘恢复pth\n",230 "#@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",231 "\n",232 "#@markdown 模型名\n",233 "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",234 "#@markdown 模型epoch\n",235 "MODELEPOCH = 7500 #@param {type:\"integer\"}\n",236 "\n",237 "!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",238 "\n",239 "!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",240 "!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",241 "!cp /content/drive/MyDrive/*.index /content/\n",242 "!cp /content/drive/MyDrive/*.npy /content/\n",243 "!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"244 ],245 "metadata": {246 "id": "OVQoLQJXS7WX"247 },248 "execution_count": null,249 "outputs": []250 },251 {252 "cell_type": "code",253 "source": [254 "#@title 手动预处理（不推荐）\n",255 "#@markdown 模型名\n",256 "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",257 "#@markdown 采样率\n",258 "BITRATE = 48000 #@param {type:\"integer\"}\n",259 "#@markdown 使用的进程数\n",260 "THREADCOUNT = 8 #@param {type:\"integer\"}\n",261 "\n",262 "!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True\n"263 ],264 "metadata": {265 "id": "ZKAyuKb9J6dz"266 },267 "execution_count": null,268 "outputs": []269 },270 {271 "cell_type": "code",272 "source": [273 "#@title 手动提取特征（不推荐）\n",274 "#@markdown 模型名\n",275 "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",276 "#@markdown 使用的进程数\n",277 "THREADCOUNT = 8 #@param {type:\"integer\"}\n",278 "#@markdown 音高提取算法\n",279 "ALGO = \"harvest\" #@param {type:\"string\"}\n",280 "\n",281 "!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",282 "\n",283 "!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME}\n"284 ],285 "metadata": {286 "id": "CrxJqzAUKmPJ"287 },288 "execution_count": null,289 "outputs": []290 },291 {292 "cell_type": "code",293 "source": [294 "#@title 手动训练（不推荐）\n",295 "#@markdown 模型名\n",296 "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",297 "#@markdown 使用的GPU\n",298 "USEGPU = \"0\" #@param {type:\"string\"}\n",299 "#@markdown 批大小\n",300 "BATCHSIZE = 32 #@param {type:\"integer\"}\n",301 "#@markdown 停止的epoch\n",302 "MODELEPOCH = 3200 #@param {type:\"integer\"}\n",303 "#@markdown 保存epoch间隔\n",304 "EPOCHSAVE = 100 #@param {type:\"integer\"}\n",305 "#@markdown 采样率\n",306 "MODELSAMPLE = \"48k\" #@param {type:\"string\"}\n",307 "#@markdown 是否缓存训练集\n",308 "CACHEDATA = 1 #@param {type:\"integer\"}\n",309 "#@markdown 是否仅保存最新的ckpt文件\n",310 "ONLYLATEST = 0 #@param {type:\"integer\"}\n",311 "\n",312 "!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}\n"313 ],314 "metadata": {315 "id": "IMLPLKOaKj58"316 },317 "execution_count": null,318 "outputs": []319 },320 {321 "cell_type": "code",322 "source": [323 "#@title 删除其它pth，只留选中的（慎点，仔细看代码）\n",324 "#@markdown 模型名\n",325 "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",326 "#@markdown 选中模型epoch\n",327 "MODELEPOCH = 9600 #@param {type:\"integer\"}\n",328 "\n",329 "!echo \"备份选中的模型。。。\"\n",330 "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",331 "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",332 "\n",333 "!echo \"正在删除。。。\"\n",334 "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",335 "!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",336 "\n",337 "!echo \"恢复选中的模型。。。\"\n",338 "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth \n",339 "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",340 "\n",341 "!echo \"删除完成\"\n",342 "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"343 ],344 "metadata": {345 "id": "haYA81hySuDl"346 },347 "execution_count": null,348 "outputs": []349 },350 {351 "cell_type": "code",352 "source": [353 "#@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",354 "#@markdown 模型名\n",355 "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",356 "#@markdown 选中模型epoch\n",357 "MODELEPOCH = 9600 #@param {type:\"integer\"}\n",358 "\n",359 "!echo \"备份选中的模型。。。\"\n",360 "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",361 "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",362 "\n",363 "!echo \"正在删除。。。\"\n",364 "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",365 "!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",366 "\n",367 "!echo \"恢复选中的模型。。。\"\n",368 "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth \n",369 "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",370 "\n",371 "!echo \"删除完成\"\n",372 "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"373 ],374 "metadata": {375 "id": "QhSiPTVPoIRh"376 },377 "execution_count": null,378 "outputs": []379 }380 ]381}