Spaces:
Sleeping
Sleeping
File size: 25,362 Bytes
85ce65e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 |
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "2q0l56aFQhAM"
},
"source": [
"# Terms of Use\n",
"\n",
"### Please solve the authorization problem of the dataset on your own. You shall be solely responsible for any problems caused by the use of non-authorized datasets for training and all consequences thereof.The repository and its maintainer, svc develop team, have nothing to do with the consequences!\n",
"\n",
"1. This project is established for academic exchange purposes only and is intended for communication and learning purposes. It is not intended for production environments.\n",
"2. Any videos based on sovits that are published on video platforms must clearly indicate in the description that they are used for voice changing and specify the input source of the voice or audio, for example, using videos or audios published by others and separating the vocals as input source for conversion, which must provide clear original video or music links. If your own voice or other synthesized voices from other commercial vocal synthesis software are used as the input source for conversion, you must also explain it in the description.\n",
"3. You shall be solely responsible for any infringement problems caused by the input source. When using other commercial vocal synthesis software as input source, please ensure that you comply with the terms of use of the software. Note that many vocal synthesis engines clearly state in their terms of use that they cannot be used for input source conversion.\n",
"4. Continuing to use this project is deemed as agreeing to the relevant provisions stated in this repository README. This repository README has the obligation to persuade, and is not responsible for any subsequent problems that may arise.\n",
"5. If you distribute this repository's code or publish any results produced by this project publicly (including but not limited to video sharing platforms), please indicate the original author and code source (this repository).\n",
"6. If you use this project for any other plan, please contact and inform the author of this repository in advance. Thank you very much.\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "M_RcDbVPhivj"
},
"source": [
"## **Note:**\n",
"## **Make sure there is no a directory named `sovits4data` in your google drive at the first time you use this notebook.**\n",
"## **It will be created to store some necessary files.** \n",
"## **For sure you can change it to another directory by modifying `sovits_data_dir` variable.**"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "fHaw6hGEa_Nk"
},
"source": [
"# **Initialize environment**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "0gQcIZ8RsOkn"
},
"outputs": [],
"source": [
"#@title Connect to colab runtime and check GPU\n",
"\n",
"#@markdown # Connect to colab runtime and check GPU\n",
"\n",
"#@markdown\n",
"\n",
"!nvidia-smi"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "0YUGpYrXhMck"
},
"outputs": [],
"source": [
"#@title Clone repository and install requirements\n",
"\n",
"#@markdown # Clone repository and install requirements\n",
"\n",
"#@markdown\n",
"\n",
"#@markdown ### After the execution is completed, the runtime will **automatically restart**\n",
"\n",
"#@markdown\n",
"\n",
"!git clone https://github.com/svc-develop-team/so-vits-svc -b 4.1-Stable\n",
"%cd /content/so-vits-svc\n",
"%pip install --upgrade pip setuptools\n",
"%pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu118\n",
"exit()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "wmUkpUmfn_Hs"
},
"outputs": [],
"source": [
"#@title Mount google drive and select which directories to sync with google drive\n",
"\n",
"#@markdown # Mount google drive and select which directories to sync with google drive\n",
"\n",
"#@markdown\n",
"\n",
"from google.colab import drive\n",
"drive.mount(\"/content/drive\")\n",
"\n",
"#@markdown Directory to store **necessary files**, dont miss the slash at the end👇.\n",
"sovits_data_dir = \"/content/drive/MyDrive/sovits4data/\" #@param {type:\"string\"}\n",
"#@markdown By default it will create a `sovits4data/` folder in your google drive.\n",
"RAW_DIR = sovits_data_dir + \"raw/\"\n",
"RESULTS_DIR = sovits_data_dir + \"results/\"\n",
"FILELISTS_DIR = sovits_data_dir + \"filelists/\"\n",
"CONFIGS_DIR = sovits_data_dir + \"configs/\"\n",
"LOGS_DIR = sovits_data_dir + \"logs/44k/\"\n",
"\n",
"#@markdown\n",
"\n",
"#@markdown ### These folders will be synced with your google drvie\n",
"\n",
"#@markdown ### **Strongly recommend to check all.**\n",
"\n",
"#@markdown Sync **input audios** and **output audios**\n",
"sync_raw_and_results = True #@param {type:\"boolean\"}\n",
"if sync_raw_and_results:\n",
" !mkdir -p {RAW_DIR}\n",
" !mkdir -p {RESULTS_DIR}\n",
" !rm -rf /content/so-vits-svc/raw\n",
" !rm -rf /content/so-vits-svc/results\n",
" !ln -s {RAW_DIR} /content/so-vits-svc/raw\n",
" !ln -s {RESULTS_DIR} /content/so-vits-svc/results\n",
"\n",
"#@markdown Sync **config** and **models**\n",
"sync_configs_and_logs = True #@param {type:\"boolean\"}\n",
"if sync_configs_and_logs:\n",
" !mkdir -p {FILELISTS_DIR}\n",
" !mkdir -p {CONFIGS_DIR}\n",
" !mkdir -p {LOGS_DIR}\n",
" !rm -rf /content/so-vits-svc/filelists\n",
" !rm -rf /content/so-vits-svc/configs\n",
" !rm -rf /content/so-vits-svc/logs/44k\n",
" !ln -s {FILELISTS_DIR} /content/so-vits-svc/filelists\n",
" !ln -s {CONFIGS_DIR} /content/so-vits-svc/configs\n",
" !ln -s {LOGS_DIR} /content/so-vits-svc/logs/44k"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "G_PMPCN6wvgZ"
},
"outputs": [],
"source": [
"#@title Get pretrained model(Optional but strongly recommend).\n",
"\n",
"#@markdown # Get pretrained model(Optional but strongly recommend).\n",
"\n",
"#@markdown\n",
"\n",
"#@markdown - Pre-trained model files: `G_0.pth` `D_0.pth`\n",
"#@markdown - Place them under /sovits4data/logs/44k/ in your google drive manualy\n",
"\n",
"#@markdown Get them from svc-develop-team(TBD) or anywhere else.\n",
"\n",
"#@markdown Although the pretrained model generally does not cause any copyright problems, please pay attention to it. For example, ask the author in advance, or the author has indicated the feasible use in the description clearly.\n",
"\n",
"download_pretrained_model = True #@param {type:\"boolean\"}\n",
"D_0_URL = \"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth\" #@param [\"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth\", \"https://huggingface.co/1asbgdh/sovits4.0-volemb-vec768/resolve/main/clean_D_320000.pth\", \"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/vol_emb/clean_D_320000.pth\"] {allow-input: true}\n",
"G_0_URL = \"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth\" #@param [\"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth\", \"https://huggingface.co/1asbgdh/sovits4.0-volemb-vec768/resolve/main/clean_G_320000.pth\", \"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/vol_emb/clean_G_320000.pth\"] {allow-input: true}\n",
"\n",
"download_pretrained_diffusion_model = True #@param {type:\"boolean\"}\n",
"diff_model_URL = \"https://huggingface.co/datasets/ms903/Diff-SVC-refactor-pre-trained-model/resolve/main/fix_pitch_add_vctk_600k/model_0.pt\" #@param {type:\"string\"}\n",
"\n",
"%cd /content/so-vits-svc\n",
"\n",
"if download_pretrained_model:\n",
" !curl -L {D_0_URL} -o logs/44k/D_0.pth\n",
" !md5sum logs/44k/D_0.pth\n",
" !curl -L {G_0_URL} -o logs/44k/G_0.pth\n",
" !md5sum logs/44k/G_0.pth\n",
"\n",
"if download_pretrained_diffusion_model:\n",
" !mkdir -p logs/44k/diffusion\n",
" !curl -L {diff_model_URL} -o logs/44k/diffusion/model_0.pt\n",
" !md5sum logs/44k/diffusion/model_0.pt"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "k1qadJBFehMo"
},
"source": [
"# **Dataset preprocessing**"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "kBlju6Q3lSM6"
},
"source": [
"Pack and upload your raw dataset(dataset_raw/) to your google drive.\n",
"\n",
"Makesure the file structure in your zip file looks like this:\n",
"\n",
"```\n",
"YourZIPforSingleSpeakers.zip\n",
"└───speaker\n",
" ├───xxx1-xxx1.wav\n",
" ├───...\n",
" └───Lxx-0xx8.wav\n",
"```\n",
"\n",
"```\n",
"YourZIPforMultipleSpeakers.zip\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",
"**Even if there is only one speaker, a folder named `{speaker_name}` is needed.**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "U05CXlAipvJR"
},
"outputs": [],
"source": [
"#@title Get raw dataset from google drive\n",
"\n",
"#@markdown # Get raw dataset from google drive\n",
"\n",
"#@markdown\n",
"\n",
"#@markdown Directory where **your zip file** located in, dont miss the slash at the end👇.\n",
"sovits_data_dir = \"/content/drive/MyDrive/sovits4data/\" #@param {type:\"string\"}\n",
"#@markdown Filename of **your zip file**, do NOT be \"dataset.zip\"\n",
"zip_filename = \"YourZIPFilenameofRawDataset.zip\" #@param {type:\"string\"}\n",
"ZIP_PATH = sovits_data_dir + zip_filename\n",
"\n",
"!unzip -od /content/so-vits-svc/dataset_raw {ZIP_PATH}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "_ThKTzYs5CfL"
},
"outputs": [],
"source": [
"#@title Resample to 44100Hz and mono\n",
"\n",
"#@markdown # Resample to 44100Hz and mono\n",
"\n",
"#@markdown\n",
"\n",
"%cd /content/so-vits-svc\n",
"!python resample.py"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "svITReeL5N8K"
},
"outputs": [],
"source": [
"#@title Divide filelists and generate config.json\n",
"\n",
"#@markdown # Divide filelists and generate config.json\n",
"\n",
"#@markdown\n",
"\n",
"%cd /content/so-vits-svc\n",
"\n",
"speech_encoder = \"vec768l12\" #@param [\"vec768l12\", \"vec256l9\", \"hubertsoft\", \"whisper-ppg\", \"whisper-ppg-large\"]\n",
"use_vol_aug = False #@param {type:\"boolean\"}\n",
"vol_aug = \"--vol_aug\" if use_vol_aug else \"\"\n",
"\n",
"from pretrain.meta import download_dict\n",
"download_dict = download_dict()\n",
"\n",
"url = download_dict[speech_encoder][\"url\"]\n",
"output = download_dict[speech_encoder][\"output\"]\n",
"\n",
"import os\n",
"if not os.path.exists(output):\n",
" !curl -L {url} -o {output}\n",
" !md5sum {output}\n",
"\n",
"!python preprocess_flist_config.py --speech_encoder={speech_encoder} {vol_aug}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "xHUXMi836DMe"
},
"outputs": [],
"source": [
"#@title Generate hubert and f0\n",
"\n",
"#@markdown # Generate hubert and f0\n",
"\n",
"#@markdown\n",
"%cd /content/so-vits-svc\n",
"\n",
"f0_predictor = \"crepe\" #@param [\"crepe\", \"pm\", \"dio\", \"harvest\", \"rmvpe\", \"fcpe\"]\n",
"use_diff = True #@param {type:\"boolean\"}\n",
"\n",
"import os\n",
"if f0_predictor == \"rmvpe\" and not os.path.exists(\"./pretrain/rmvpe.pt\"):\n",
" !curl -L https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/rmvpe.pt -o pretrain/rmvpe.pt\n",
"\n",
"if f0_predictor == \"fcpe\" and not os.path.exists(\"./pretrain/fcpe.pt\"):\n",
" !curl -L https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/fcpe.pt -o pretrain/fcpe.pt\n",
"\n",
"\n",
"diff_param = \"\"\n",
"if use_diff:\n",
" diff_param = \"--use_diff\"\n",
"\n",
" if not os.path.exists(\"./pretrain/nsf_hifigan/model\"):\n",
" !curl -L https://github.com/openvpi/vocoders/releases/download/nsf-hifigan-v1/nsf_hifigan_20221211.zip -o nsf_hifigan_20221211.zip\n",
" !md5sum nsf_hifigan_20221211.zip\n",
" !unzip nsf_hifigan_20221211.zip\n",
" !rm -rf pretrain/nsf_hifigan\n",
" !mv -v nsf_hifigan pretrain\n",
"\n",
"!python preprocess_hubert_f0.py --f0_predictor={f0_predictor} {diff_param}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Wo4OTmTAUXgj"
},
"outputs": [],
"source": [
"#@title Save the preprocessed dataset to google drive\n",
"\n",
"#@markdown # Save the preprocessed dataset to google drive\n",
"\n",
"#@markdown\n",
"\n",
"#@markdown You can save the dataset and related files to your google drive for the next training\n",
"\n",
"#@markdown **Directory for saving**, dont miss the slash at the end👇.\n",
"sovits_data_dir = \"/content/drive/MyDrive/sovits4data/\" #@param {type:\"string\"}\n",
"\n",
"#@markdown There will be a `dataset.zip` contained `dataset/` in your google drive, which is preprocessed data.\n",
"\n",
"!mkdir -p {sovits_data_dir}\n",
"!zip -r dataset.zip /content/so-vits-svc/dataset\n",
"!cp -vr dataset.zip \"{sovits_data_dir}\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "P2G6v_6zblWK"
},
"outputs": [],
"source": [
"#@title Unzip preprocessed dataset from google drive directly if you have preprocessed already.\n",
"\n",
"#@markdown # Unzip preprocessed dataset from google drive directly if you have preprocessed already.\n",
"\n",
"#@markdown\n",
"\n",
"#@markdown Directory where **your preprocessed dataset** located in, dont miss the slash at the end👇.\n",
"sovits_data_dir = \"/content/drive/MyDrive/sovits4data/\" #@param {type:\"string\"}\n",
"CONFIG = sovits_data_dir + \"configs/\"\n",
"FILELISTS = sovits_data_dir + \"filelists/\"\n",
"DATASET = sovits_data_dir + \"dataset.zip\"\n",
"\n",
"!cp -vr {CONFIG} /content/so-vits-svc/\n",
"!cp -vr {FILELISTS} /content/so-vits-svc/\n",
"!unzip {DATASET} -d /"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "ENoH-pShel7w"
},
"source": [
"# **Trainning**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "-hEFFTCfZf57"
},
"outputs": [],
"source": [
"#@title Start training\n",
"\n",
"#@markdown # Start training\n",
"\n",
"#@markdown If you want to use pre-trained models, upload them to /sovits4data/logs/44k/ in your google drive manualy.\n",
"\n",
"#@markdown\n",
"\n",
"%cd /content/so-vits-svc\n",
"\n",
"#@markdown Whether to enable tensorboard\n",
"tensorboard_on = True #@param {type:\"boolean\"}\n",
"\n",
"if tensorboard_on:\n",
" %load_ext tensorboard\n",
" %tensorboard --logdir logs/44k\n",
"\n",
"config_path = \"configs/config.json\"\n",
"\n",
"from pretrain.meta import get_speech_encoder\n",
"url, output = get_speech_encoder(config_path)\n",
"\n",
"import os\n",
"if not os.path.exists(output):\n",
" !curl -L {url} -o {output}\n",
"\n",
"!python train.py -c {config_path} -m 44k"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ZThaMxmIJgWy"
},
"outputs": [],
"source": [
"#@title Train cluster model (Optional)\n",
"\n",
"#@markdown # Train cluster model (Optional)\n",
"\n",
"#@markdown #### Details see [README.md#cluster-based-timbre-leakage-control](https://github.com/svc-develop-team/so-vits-svc#cluster-based-timbre-leakage-control)\n",
"\n",
"#@markdown\n",
"\n",
"%cd /content/so-vits-svc\n",
"!python cluster/train_cluster.py --gpu"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#@title Train index model (Optional)\n",
"\n",
"#@markdown # Train index model (Optional)\n",
"\n",
"#@markdown #### Details see [README.md#feature-retrieval](https://github.com/svc-develop-team/so-vits-svc#feature-retrieval)\n",
"\n",
"#@markdown\n",
"\n",
"%cd /content/so-vits-svc\n",
"!python train_index.py -c configs/config.json"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#@title Train diffusion model (Optional)\n",
"\n",
"#@markdown # Train diffusion model (Optional)\n",
"\n",
"#@markdown #### Details see [README.md#-about-shallow-diffusion](https://github.com/svc-develop-team/so-vits-svc#-about-shallow-diffusion)\n",
"\n",
"#@markdown\n",
"\n",
"%cd /content/so-vits-svc\n",
"\n",
"import os\n",
"if not os.path.exists(\"./pretrain/nsf_hifigan/model\"):\n",
" !curl -L https://github.com/openvpi/vocoders/releases/download/nsf-hifigan-v1/nsf_hifigan_20221211.zip -o nsf_hifigan_20221211.zip\n",
" !unzip nsf_hifigan_20221211.zip\n",
" !rm -rf pretrain/nsf_hifigan\n",
" !mv -v nsf_hifigan pretrain\n",
"\n",
"#@markdown Whether to enable tensorboard\n",
"tensorboard_on = True #@param {type:\"boolean\"}\n",
"\n",
"if tensorboard_on:\n",
" %load_ext tensorboard\n",
" %tensorboard --logdir logs/44k\n",
"\n",
"!python train_diff.py -c configs/diffusion.yaml"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# keep colab alive\n",
"Open the devtools and copy & paste to run the scrips.\n",
"\n",
"\n",
"```JavaScript\n",
"const ping = () => {\n",
" const btn = document.querySelector(\"colab-connect-button\");\n",
" const inner_btn = btn.shadowRoot.querySelector(\"#connect\");\n",
" if (inner_btn) {\n",
" inner_btn.click();\n",
" console.log(\"Clicked on connect button\");\n",
" } else {\n",
" console.log(\"connect button not found\");\n",
" }\n",
"\n",
" const nextTime = 50000 + Math.random() * 10000;\n",
"\n",
" setTimeout(ping, nextTime);\n",
"};\n",
"\n",
"ping();\n",
"```"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "oCnbX-OT897k"
},
"source": [
"# **Inference**\n",
"### Upload wav files from this notebook\n",
"### **OR**\n",
"### Upload to `sovits4data/raw/` in your google drive manualy (should be faster)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#title Download nsf_hifigan if you need it\n",
"\n",
"%cd /content/so-vits-svc\n",
"!curl -L https://github.com/openvpi/vocoders/releases/download/nsf-hifigan-v1/nsf_hifigan_20221211.zip -o /content/so-vits-svc/nsf_hifigan_20221211.zip\n",
"!unzip nsf_hifigan_20221211.zip\n",
"!rm -rf pretrain/nsf_hifigan\n",
"!mv -v nsf_hifigan pretrain\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 75
},
"executionInfo": {
"elapsed": 94633,
"status": "ok",
"timestamp": 1678591088790,
"user": {
"displayName": "謬紗特",
"userId": "09445825975794260265"
},
"user_tz": -480
},
"id": "XUsmGkgCMD_Q",
"outputId": "8bbfde13-030a-4ba0-bbdb-7eb6b89c02b4"
},
"outputs": [],
"source": [
"#@title Upload wav files, the filename should not contain any special symbols like `#` `$` `(` `)`\n",
"\n",
"#@markdown # Upload wav files, the filename should not contain any special symbols like `#` `$` `(` `)`\n",
"\n",
"#@markdown\n",
"\n",
"%cd /content/so-vits-svc\n",
"%run wav_upload.py --type audio"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "dYnKuKTIj3z1"
},
"outputs": [],
"source": [
"#@title Start inference (and download)\n",
"\n",
"#@markdown # Start inference (and download)\n",
"\n",
"#@markdown Parameters see [README.MD#Inference](https://github.com/svc-develop-team/so-vits-svc#-inference)\n",
"\n",
"#@markdown\n",
"\n",
"wav_filename = \"YourWAVFile.wav\" #@param {type:\"string\"}\n",
"model_filename = \"G_210000.pth\" #@param {type:\"string\"}\n",
"model_path = \"/content/so-vits-svc/logs/44k/\" + model_filename\n",
"speaker = \"YourSpeaker\" #@param {type:\"string\"}\n",
"trans = \"0\" #@param {type:\"string\"}\n",
"cluster_infer_ratio = \"0\" #@param {type:\"string\"}\n",
"auto_predict_f0 = False #@param {type:\"boolean\"}\n",
"apf = \"\"\n",
"if auto_predict_f0:\n",
" apf = \" -a \"\n",
"\n",
"f0_predictor = \"crepe\" #@param [\"crepe\", \"pm\", \"dio\", \"harvest\", \"rmvpe\", \"fcpe\"]\n",
"\n",
"enhance = False #@param {type:\"boolean\"}\n",
"ehc = \"\"\n",
"if enhance:\n",
" ehc = \" -eh \"\n",
"#@markdown\n",
"\n",
"#@markdown Generally keep default:\n",
"config_filename = \"config.json\" #@param {type:\"string\"}\n",
"config_path = \"/content/so-vits-svc/configs/\" + config_filename\n",
"\n",
"from pretrain.meta import get_speech_encoder\n",
"url, output = get_speech_encoder(config_path)\n",
"\n",
"import os\n",
"\n",
"if f0_predictor == \"rmvpe\" and not os.path.exists(\"./pretrain/rmvpe.pt\"):\n",
" !curl -L https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/rmvpe.pt -o pretrain/rmvpe.pt\n",
"\n",
"if f0_predictor == \"fcpe\" and not os.path.exists(\"./pretrain/fcpe.pt\"):\n",
" !curl -L https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/fcpe.pt -o pretrain/fcpe.pt\n",
"\n",
"if not os.path.exists(output):\n",
" !curl -L {url} -o {output}\n",
"\n",
"kmeans_filenname = \"kmeans_10000.pt\" #@param {type:\"string\"}\n",
"kmeans_path = \"/content/so-vits-svc/logs/44k/\" + kmeans_filenname\n",
"slice_db = \"-40\" #@param {type:\"string\"}\n",
"wav_format = \"flac\" #@param {type:\"string\"}\n",
"\n",
"key = \"auto\" if auto_predict_f0 else f\"{trans}key\"\n",
"cluster_name = \"\" if cluster_infer_ratio == \"0\" else f\"_{cluster_infer_ratio}\"\n",
"isdiffusion = \"sovits\"\n",
"wav_output = f\"/content/so-vits-svc/results/{wav_filename}_{key}_{speaker}{cluster_name}_{isdiffusion}_{f0_predictor}.{wav_format}\"\n",
"\n",
"%cd /content/so-vits-svc\n",
"!python inference_main.py -n {wav_filename} -m {model_path} -s {speaker} -t {trans} -cr {cluster_infer_ratio} -c {config_path} -cm {kmeans_path} -sd {slice_db} -wf {wav_format} {apf} --f0_predictor={f0_predictor} {ehc}\n",
"\n",
"#@markdown\n",
"\n",
"#@markdown If you dont want to download from here, uncheck this.\n",
"download_after_inference = True #@param {type:\"boolean\"}\n",
"\n",
"if download_after_inference:\n",
" from google.colab import files\n",
" files.download(wav_output)"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"provenance": [
{
"file_id": "19fxpo-ZoL_ShEUeZIZi6Di-YioWrEyhR",
"timestamp": 1678516497580
},
{
"file_id": "1rCUOOVG7-XQlVZuWRAj5IpGrMM8t07pE",
"timestamp": 1673086970071
},
{
"file_id": "1Ul5SmzWiSHBj0MaKA0B682C-RZKOycwF",
"timestamp": 1670483515921
}
]
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.16"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|