Spaces:
Running
Running
File size: 11,149 Bytes
9791162 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "SggegFslkbbK"
},
"source": [
"https://github.com/PlayVoice/so-vits-svc-5.0/\n",
"\n",
"↑原仓库\n",
"\n",
"*《colab保持连接的方法》*https://zhuanlan.zhihu.com/p/144629818\n",
"\n",
"预览版本，可使用预设模型进行推理"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "M1MdDryJP73G"
},
"source": [
"# **环境配置&必要文件下载**\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "xfJWCr_EkO2i"
},
"outputs": [],
"source": [
"#@title 看看抽了个啥卡~~基本都是T4~~\n",
"!nvidia-smi"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "nMspj8t3knR6"
},
"outputs": [],
"source": [
"#@title 克隆github仓库\n",
"!git clone https://github.com/PlayVoice/so-vits-svc-5.0/ -b bigvgan-mix-v2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Kj2j81K6kubj"
},
"outputs": [],
"source": [
"#@title 安装依赖&下载必要文件\n",
"%cd /content/so-vits-svc-5.0\n",
"\n",
"!pip install -r requirements.txt\n",
"!pip install --upgrade pip setuptools numpy numba\n",
"\n",
"!wget -P hubert_pretrain/ https://github.com/bshall/hubert/releases/download/v0.1/hubert-soft-0d54a1f4.pt\n",
"!wget -P whisper_pretrain/ https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt\n",
"!wget -P speaker_pretrain/ https://github.com/PlayVoice/so-vits-svc-5.0/releases/download/dependency/best_model.pth.tar\n",
"!wget -P crepe/assets https://github.com/PlayVoice/so-vits-svc-5.0/releases/download/dependency/full.pth\n",
"!wget -P vits_pretrain https://github.com/PlayVoice/so-vits-svc-5.0/releases/download/5.0/sovits5.0.pretrain.pth"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "v9zHS9VXly9b"
},
"outputs": [],
"source": [
"#@title 加载Google云端硬盘\n",
"from google.colab import drive\n",
"drive.mount('/content/drive')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "hZ5KH8NgQ7os"
},
"source": [
"# 包含多说话人的推理预览"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "2o6m3D0IsphU"
},
"outputs": [],
"source": [
"#@title 提取内容编码\n",
"\n",
"#@markdown **将处理好的\" .wav \"输入源文件上传到云盘根目录，并修改以下选项**\n",
"\n",
"#@markdown **\" .wav \"文件【文件名】**\n",
"input = \"\\u30AE\\u30BF\\u30FC\\u3068\\u5B64\\u72EC\\u3068\\u84BC\\u3044\\u60D1\\u661F\" #@param {type:\"string\"}\n",
"input_path = \"/content/drive/MyDrive/\"\n",
"input_name = input_path + input\n",
"!PYTHONPATH=. python whisper/inference.py -w {input_name}.wav -p test.ppg.npy"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "A7nvX5mRlwJ7"
},
"outputs": [],
"source": [
"#@title 推理\n",
"\n",
"#@markdown **将处理好的\" .wav \"输入源文件上传到云盘根目录，并修改以下选项**\n",
"\n",
"#@markdown **\" .wav \"文件【文件名】**\n",
"input = \"\\u30AE\\u30BF\\u30FC\\u3068\\u5B64\\u72EC\\u3068\\u84BC\\u3044\\u60D1\\u661F\" #@param {type:\"string\"}\n",
"input_path = \"/content/drive/MyDrive/\"\n",
"input_name = input_path + input\n",
"#@markdown **指定说话人（0001~0056）（推荐0022、0030、0047、0051）**\n",
"speaker = \"0002\" #@param {type:\"string\"}\n",
"!PYTHONPATH=. python svc_inference.py --config configs/base.yaml --model vits_pretrain/sovits5.0.pretrain.pth --spk ./configs/singers/singer{speaker}.npy --wave {input_name}.wav --ppg test.ppg.npy"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "F8oerogXyd3u"
},
"source": [
"推理结果保存在根目录，文件名为svc_out.wav"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qKX17GElPuso"
},
"source": [
"# 训练"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "sVe0lEGWQBLU"
},
"source": [
"将音频剪裁为小于30秒的音频段，响度匹配并修改为单声道，预处理时会进行重采样所以对采样率无要求。（但是降低采样率的操作会降低你的数据质量）\n",
"\n",
"**使用Adobe Audition™的响度匹配功能可以一次性完成重采样修改声道和响度匹配。**\n",
"\n",
"之后将音频文件保存为以下文件结构：\n",
"```\n",
"dataset_raw\n",
"├───speaker0\n",
"│ ├───xxx1-xxx1.wav\n",
"│ ├───...\n",
"│ └───Lxx-0xx8.wav\n",
"└───speaker1\n",
" ├───xx2-0xxx2.wav\n",
" ├───...\n",
" └───xxx7-xxx007.wav\n",
"```\n",
"\n",
"打包为zip格式，命名为data.zip，上传到网盘根目录。"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "vC8IthV8VYgy"
},
"outputs": [],
"source": [
"#@title 从云盘获取数据集\n",
"!unzip -d /content/so-vits-svc-5.0/ /content/drive/MyDrive/data.zip #自行修改路径与文件名"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "J101PiFUSL1N"
},
"outputs": [],
"source": [
"#@title 重采样\n",
"# 生成采样率16000Hz音频, 存储路径为：./data_svc/waves-16k\n",
"!python prepare/preprocess_a.py -w ./dataset_raw -o ./data_svc/waves-16k -s 16000\n",
"# 生成采样率32000Hz音频, 存储路径为：./data_svc/waves-32k\n",
"!python prepare/preprocess_a.py -w ./dataset_raw -o ./data_svc/waves-32k -s 32000"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ZpxeYJCBSbgf"
},
"outputs": [],
"source": [
"#@title 提取f0\n",
"!python prepare/preprocess_f0.py -w data_svc/waves-16k/ -p data_svc/pitch"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "7VasDGhDSlP5"
},
"outputs": [],
"source": [
"#@title 使用16k音频，提取内容编码\n",
"!PYTHONPATH=. python prepare/preprocess_ppg.py -w data_svc/waves-16k/ -p data_svc/whisper"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#@title 使用16k音频，提取内容编码\n",
"!PYTHONPATH=. python prepare/preprocess_hubert.py -w data_svc/waves-16k/ -v data_svc/hubert"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ovRqQUINSoII"
},
"outputs": [],
"source": [
"#@title 提取音色特征\n",
"!PYTHONPATH=. python prepare/preprocess_speaker.py data_svc/waves-16k/ data_svc/speaker"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "s8Ba8Fd1bzzX"
},
"outputs": [],
"source": [
"#（解决“.ipynb_checkpoints”相关的错）\n",
"!rm -rf \"find -type d -name .ipynb_checkpoints\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ic9q599_b0Ae"
},
"outputs": [],
"source": [
"#（解决“.ipynb_checkpoints”相关的错）\n",
"!rm -rf .ipynb_checkpoints\n",
"!find . -name \".ipynb_checkpoints\" -exec rm -rf {} \\;"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "QamG3_B6o3vF"
},
"outputs": [],
"source": [
"#@title 提取平均音色\n",
"!PYTHONPATH=. python prepare/preprocess_speaker_ave.py data_svc/speaker/ data_svc/singer"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "3wBmyQHvSs6K"
},
"outputs": [],
"source": [
"#@title 提取spec\n",
"!PYTHONPATH=. python prepare/preprocess_spec.py -w data_svc/waves-32k/ -s data_svc/specs"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "tUcljCLbS5O3"
},
"outputs": [],
"source": [
"#@title 生成索引\n",
"!python prepare/preprocess_train.py"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "30fXnscFS7Wo"
},
"outputs": [],
"source": [
"#@title 训练文件调试\n",
"!PYTHONPATH=. python prepare/preprocess_zzz.py"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "hacR8qDFVOWo"
},
"outputs": [],
"source": [
"#@title 设定模型备份\n",
"#@markdown **是否备份模型到云盘，colab随时爆炸建议备份，默认保存到云盘根目录Sovits5.0文件夹**\n",
"Save_to_drive = True #@param {type:\"boolean\"}\n",
"if Save_to_drive:\n",
" !mkdir -p /content/so-vits-svc-5.0/chkpt/\n",
" !rm -rf /content/so-vits-svc-5.0/chkpt/\n",
" !mkdir -p /content/drive/MyDrive/Sovits5.0\n",
" !ln -s /content/drive/MyDrive/Sovits5.0 /content/so-vits-svc-5.0/chkpt/"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "5BIiKIAoU3Kd"
},
"outputs": [],
"source": [
"#@title 开始训练\n",
"%load_ext tensorboard\n",
"%tensorboard --logdir /content/so-vits-svc-5.0/logs/\n",
"\n",
"!PYTHONPATH=. python svc_trainer.py -c configs/base.yaml -n sovits5.0"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"provenance": []
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|