Spaces:
Runtime error
Runtime error
File size: 28,979 Bytes
8ef89ca | 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 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "0pKllbPyK_BC"
},
"source": [
"## **Applio NoUI**\n",
"A simple, high-quality voice conversion tool focused on ease of use and performance.\n",
"\n",
"[Support](https://discord.gg/urxFjYmYYh) — [GitHub](https://github.com/IAHispano/Applio) — [Terms of Use](https://github.com/IAHispano/Applio/blob/main/TERMS_OF_USE.md)\n",
"\n",
"<br>\n",
"\n",
"---\n",
"\n",
"<br>\n",
"\n",
"#### **Acknowledgments**\n",
"\n",
"To all external collaborators for their special help in the following areas:\n",
"* Hina (Encryption method)\n",
"* Poopmaster (Extra section)\n",
"* Shirou (UV installer)\n",
"* Bruno5430 (AutoBackup code and general notebook maintenance)\n",
"\n",
"#### **Disclaimer**\n",
"By using Applio, you agree to comply with ethical and legal standards, respect intellectual property and privacy rights, avoid harmful or prohibited uses, and accept full responsibility for any outcomes, while Applio disclaims liability and reserves the right to amend these terms."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ymMCTSD6m8qV"
},
"source": [
"### **Install Applio**\n",
"If the runtime restarts, re-run the installation steps."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "yFhAeKGOp9aa"
},
"outputs": [],
"source": [
"# @title Mount Google Drive\n",
"from google.colab import drive\n",
"from google.colab._message import MessageError\n",
"\n",
"try:\n",
" drive.mount(\"/content/drive\")\n",
"except MessageError:\n",
" print(\"❌ Failed to mount drive\")\n",
"\n",
"# Migrate folders to match documentation\n",
"from pathlib import Path\n",
"if Path(\"/content/drive\").is_mount():\n",
" %cd \"/content/drive/MyDrive/\"\n",
" if not Path(\"ApplioBackup/\").exists() and Path(\"RVC_Backup/\").exists():\n",
" !mv \"RVC_Backup/\" \"ApplioBackup/\"\n",
" %cd /content"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "CAXW55BQm0PP"
},
"outputs": [],
"source": [
"# @title Setup runtime environment\n",
"from multiprocessing import cpu_count\n",
"cpu_cores = cpu_count()\n",
"post_process = False\n",
"LOGS_PATH = \"/content/Applio/logs\"\n",
"BACKUPS_PATH = \"/content/drive/MyDrive/ApplioBackup\"\n",
"\n",
"%cd /content\n",
"!git config --global advice.detachedHead false\n",
"!git clone https://github.com/IAHispano/Applio --single-branch\n",
"%cd /content/Applio\n",
"!git checkout 8e161d2baffd145782241c8b1779f77d1bf7a06d\n",
"\n",
"# Install older python\n",
"!apt install python3.11 python3.11-distutils\n",
"!update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 2\n",
"!update-alternatives --set python3 /usr/bin/python3.11\n",
"\n",
"print(\"Installing requirements...\")\n",
"!curl -LsSf https://astral.sh/uv/install.sh | sh\n",
"!uv pip install -q torch==2.7.1 torchvision torchaudio==2.7.1 --upgrade --index-url https://download.pytorch.org/whl/cu128\n",
"!uv pip install -q -r requirements.txt\n",
"!uv pip install -q jupyter-ui-poll\n",
"!python core.py \"prerequisites\" --models \"True\" --pretraineds_hifigan \"True\"\n",
"print(\"Finished installing requirements!\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "YzaeMYsUE97Y"
},
"source": [
"### **Infer**\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "2miFQtlfiWy_"
},
"outputs": [],
"source": [
"# @title Sync with Google Drive\n",
"# @markdown 💾 Run this cell to automatically Save/Load models from your mounted drive\n",
"# @title\n",
"# @markdown This will merge and link your `ApplioBackup` folder from gdrive to this notebook\n",
"from IPython.display import display, clear_output\n",
"from pathlib import Path\n",
"\n",
"non_bak_folders = [\"mute\", \"reference\", \"zips\", \"mute_spin\"]\n",
"non_bak_path = \"/tmp/rvc_logs\"\n",
"\n",
"\n",
"def press_button(button):\n",
" button.disabled = True\n",
"\n",
"\n",
"def get_date(path: Path):\n",
" from datetime import datetime\n",
" return datetime.fromtimestamp(int(path.stat().st_mtime))\n",
"\n",
"\n",
"def get_size(path: Path):\n",
" !du -shx --apparent-size \"{path}\" > /tmp/size.txt\n",
" return open(\"/tmp/size.txt\").readlines().pop(0).split(\"\t\")[0] + \"B\"\n",
"\n",
"\n",
"def sync_folders(folder: Path, backup: Path):\n",
" from ipywidgets import widgets\n",
" from jupyter_ui_poll import ui_events\n",
" from time import sleep\n",
"\n",
" local = widgets.VBox([\n",
" widgets.Label(f\"Local: {LOGS_PATH.removeprefix('/content/')}/{folder.name}/\"),\n",
" widgets.Label(f\"Size: {get_size(folder)}\"),\n",
" widgets.Label(f\"Last modified: {get_date(folder)}\")\n",
" ])\n",
" remote = widgets.VBox([\n",
" widgets.Label(f\"Remote: {BACKUPS_PATH.removeprefix('/content/')}/{backup.name}/\"),\n",
" widgets.Label(f\"Size: {get_size(backup)}\"),\n",
" widgets.Label(f\"Last modified: {get_date(backup)}\")\n",
" ])\n",
" separator = widgets.VBox([\n",
" widgets.Label(\"|||\"),\n",
" widgets.Label(\"|||\"),\n",
" widgets.Label(\"|||\")\n",
" ])\n",
" radio = widgets.RadioButtons(\n",
" options=[\n",
" \"Save local model to drive\",\n",
" \"Keep remote model\"\n",
" ]\n",
" )\n",
" button = widgets.Button(\n",
" description=\"Sync\",\n",
" icon=\"upload\",\n",
" tooltip=\"Sync model\"\n",
" )\n",
" button.on_click(press_button)\n",
"\n",
" clear_output()\n",
" print(f\"Your local model '{folder.name}' is in conflict with it's copy in Google Drive.\")\n",
" print(\"Please select which one you want to keep:\")\n",
" display(widgets.Box([local, separator, remote]))\n",
" display(radio)\n",
" display(button)\n",
"\n",
" with ui_events() as poll:\n",
" while not button.disabled:\n",
" poll(10)\n",
" sleep(0.1)\n",
"\n",
" match radio.value:\n",
" case \"Save local model to drive\":\n",
" !rm -r \"{backup}\"\n",
" !mv \"{folder}\" \"{backup}\"\n",
" case \"Keep remote model\":\n",
" !rm -r \"{folder}\"\n",
"\n",
"\n",
"if Path(\"/content/drive\").is_mount():\n",
" !mkdir -p \"{BACKUPS_PATH}\"\n",
" !mkdir -p \"{non_bak_path}\"\n",
"\n",
" if not Path(LOGS_PATH).is_symlink():\n",
" for folder in non_bak_folders:\n",
" folder = Path(f\"{LOGS_PATH}/{folder}\")\n",
" backup = Path(f\"{BACKUPS_PATH}/{folder.name}\")\n",
"\n",
" !mkdir -p \"{folder}\"\n",
" !mv \"{folder}\" \"{non_bak_path}\" &> /dev/null\n",
" !rm -rf \"{folder}\"\n",
" folder = Path(f\"{non_bak_path}/{folder.name}\")\n",
" if backup.exists() and backup.resolve() != folder.resolve():\n",
" !rm -r \"{backup}\"\n",
" !ln -s \"{folder}\" \"{backup}\" &> /dev/null\n",
"\n",
" for model in Path(LOGS_PATH).iterdir():\n",
" if model.is_dir() and not model.is_symlink():\n",
" backup = Path(f\"{BACKUPS_PATH}/{model.name}\")\n",
"\n",
" if model.name == \".ipynb_checkpoints\":\n",
" continue\n",
"\n",
" if backup.exists() and backup.is_dir():\n",
" sync_folders(model, backup)\n",
" else:\n",
" !rm \"{backup}\"\n",
" !mv \"{model}\" \"{backup}\"\n",
"\n",
" !rm -r \"{LOGS_PATH}\"\n",
" !ln -s \"{BACKUPS_PATH}\" \"{LOGS_PATH}\"\n",
"\n",
" clear_output()\n",
" print(\"✅ Models are synced!\")\n",
"\n",
" else:\n",
" !rm \"{LOGS_PATH}\"\n",
" !ln -s \"{BACKUPS_PATH}\" \"{LOGS_PATH}\"\n",
" clear_output()\n",
" print(\"✅ Models already synced!\")\n",
"\n",
"else:\n",
" print(\"❌ Drive is not mounted, skipping model syncing\")\n",
" print(\"To sync your models, first mount your Google Drive and re-run this cell\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "v0EgikgjFCjE"
},
"outputs": [],
"source": [
"# @title Download model\n",
"# @markdown Hugging Face or Google Drive\n",
"model_link = \"https://huggingface.co/Darwin/Darwin/resolve/main/Darwin.zip\" # @param {type:\"string\"}\n",
"\n",
"%cd /content/Applio\n",
"!python core.py download --model_link \"{model_link}\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "lrCKEOzvDPRu"
},
"outputs": [],
"source": [
"# @title Run Inference\n",
"# @markdown Please upload the audio file to your Google Drive path `/content/drive/MyDrive` and specify its name here. For the model name, use the zip file name without the extension. Alternatively, you can check the path `/content/Applio/logs` for the model name (name of the folder).\n",
"%cd /content/Applio\n",
"from pathlib import Path\n",
"\n",
"model_name = \"Darwin\" # @param {type:\"string\"}\n",
"model_path = Path(f\"{LOGS_PATH}/{model_name}\")\n",
"if not (model_path.exists() and model_path.is_dir()):\n",
" raise FileNotFoundError(f\"Model directory not found: {model_path.resolve()}\")\n",
"\n",
"# Select either the last checkpoint or the final weight\n",
"!ls -t \"{model_path}\"/\"{model_name}\"_*e_*s.pth \"{model_path}\"/\"{model_name}\".pth 2> /dev/null | head -n 1 > /tmp/pth.txt\n",
"pth_file = open(\"/tmp/pth.txt\", \"r\").read().strip()\n",
"if pth_file == \"\":\n",
" raise FileNotFoundError(f\"No model weight found in directory: {model_path.resolve()}\\nMake sure that the file is properly named (e.g. \\\"{model_name}.pth)\\\"\")\n",
"\n",
"!ls -t \"{model_path}\"/*.index | head -n 1 > /tmp/index.txt\n",
"index_file = open(\"/tmp/index.txt\", \"r\").read().strip()\n",
"\n",
"input_path = \"/content/example.wav\" # @param {type:\"string\"}\n",
"output_path = \"/content/output.wav\"\n",
"export_format = \"WAV\" # @param ['WAV', 'MP3', 'FLAC', 'OGG', 'M4A'] {allow-input: false}\n",
"f0_method = \"rmvpe\" # @param [\"crepe\", \"crepe-tiny\", \"rmvpe\", \"fcpe\", \"hybrid[rmvpe+fcpe]\"] {allow-input: false}\n",
"f0_up_key = 0 # @param {type:\"slider\", min:-24, max:24, step:0}\n",
"rms_mix_rate = 0.8 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"protect = 0.5 # @param {type:\"slider\", min:0.0, max:0.5, step:0.1}\n",
"index_rate = 0.7 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"clean_strength = 0.7 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"split_audio = False # @param{type:\"boolean\"}\n",
"clean_audio = False # @param{type:\"boolean\"}\n",
"f0_autotune = False # @param{type:\"boolean\"}\n",
"formant_shift = False # @param{type:\"boolean\"}\n",
"formant_qfrency = 1.0 # @param {type:\"slider\", min:1.0, max:16.0, step:0.1}\n",
"formant_timbre = 1.0 # @param {type:\"slider\", min:1.0, max:16.0, step:0.1}\n",
"embedder_model = \"contentvec\" # @param [\"contentvec\", \"chinese-hubert-base\", \"japanese-hubert-base\", \"korean-hubert-base\", \"custom\"] {allow-input: false}\n",
"embedder_model_custom = \"\" # @param {type:\"string\"}\n",
"\n",
"!rm -f \"{output_path}\"\n",
"if post_process:\n",
" !python core.py infer --pitch \"{f0_up_key}\" --volume_envelope \"{rms_mix_rate}\" --index_rate \"{index_rate}\" --protect \"{protect}\" --f0_autotune \"{f0_autotune}\" --f0_method \"{f0_method}\" --input_path \"{input_path}\" --output_path \"{output_path}\" --pth_path \"{pth_file}\" --index_path \"{index_file}\" --split_audio \"{split_audio}\" --clean_audio \"{clean_audio}\" --clean_strength \"{clean_strength}\" --export_format \"{export_format}\" --embedder_model \"{embedder_model}\" --embedder_model_custom \"{embedder_model_custom}\" --formant_shifting \"{formant_shift}\" --formant_qfrency \"{formant_qfrency}\" --formant_timbre \"{formant_timbre}\" --post_process \"{post_process}\" --reverb \"{reverb}\" --pitch_shift \"{pitch_shift}\" --limiter \"{limiter}\" --gain \"{gain}\" --distortion \"{distortion}\" --chorus \"{chorus}\" --bitcrush \"{bitcrush}\" --clipping \"{clipping}\" --compressor \"{compressor}\" --delay \"{delay}\" --reverb_room_size \"{reverb_room_size}\" --reverb_damping \"{reverb_damping}\" --reverb_wet_gain \"{reverb_wet_gain}\" --reverb_dry_gain \"{reverb_dry_gain}\" --reverb_width \"{reverb_width}\" --reverb_freeze_mode \"{reverb_freeze_mode}\" --pitch_shift_semitones \"{pitch_shift_semitones}\" --limiter_threshold \"{limiter_threshold}\" --limiter_release_time \"{limiter_release_time}\" --gain_db \"{gain_db}\" --distortion_gain \"{distortion_gain}\" --chorus_rate \"{chorus_rate}\" --chorus_depth \"{chorus_depth}\" --chorus_center_delay \"{chorus_center_delay}\" --chorus_feedback \"{chorus_feedback}\" --chorus_mix \"{chorus_mix}\" --bitcrush_bit_depth \"{bitcrush_bit_depth}\" --clipping_threshold \"{clipping_threshold}\" --compressor_threshold \"{compressor_threshold}\" --compressor_ratio \"{compressor_ratio}\" --compressor_attack \"{compressor_attack}\" --compressor_release \"{compressor_release}\" --delay_seconds \"{delay_seconds}\" --delay_feedback \"{delay_feedback}\" --delay_mix \"{delay_mix}\"\n",
"else:\n",
" !python core.py infer --pitch \"{f0_up_key}\" --volume_envelope \"{rms_mix_rate}\" --index_rate \"{index_rate}\" --protect \"{protect}\" --f0_autotune \"{f0_autotune}\" --f0_method \"{f0_method}\" --input_path \"{input_path}\" --output_path \"{output_path}\" --pth_path \"{pth_file}\" --index_path \"{index_file}\" --split_audio \"{split_audio}\" --clean_audio \"{clean_audio}\" --clean_strength \"{clean_strength}\" --export_format \"{export_format}\" --embedder_model \"{embedder_model}\" --embedder_model_custom \"{embedder_model_custom}\" --formant_shifting \"{formant_shift}\" --formant_qfrency \"{formant_qfrency}\" --formant_timbre \"{formant_timbre}\" --post_process \"{post_process}\"\n",
"\n",
"if Path(output_path).exists():\n",
" from IPython.display import Audio, display\n",
" output_path = output_path.replace(\".wav\", f\".{export_format.lower()}\")\n",
" display(Audio(output_path, autoplay=True))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "J43qejJ-2Tpp"
},
"outputs": [],
"source": [
"# @title Enable post-processing effects for inference\n",
"post_process = False # @param{type:\"boolean\"}\n",
"reverb = False # @param{type:\"boolean\"}\n",
"pitch_shift = False # @param{type:\"boolean\"}\n",
"limiter = False # @param{type:\"boolean\"}\n",
"gain = False # @param{type:\"boolean\"}\n",
"distortion = False # @param{type:\"boolean\"}\n",
"chorus = False # @param{type:\"boolean\"}\n",
"bitcrush = False # @param{type:\"boolean\"}\n",
"clipping = False # @param{type:\"boolean\"}\n",
"compressor = False # @param{type:\"boolean\"}\n",
"delay = False # @param{type:\"boolean\"}\n",
"\n",
"reverb_room_size = 0.5 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"reverb_damping = 0.5 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"reverb_wet_gain = 0.0 # @param {type:\"slider\", min:-20.0, max:20.0, step:0.1}\n",
"reverb_dry_gain = 0.0 # @param {type:\"slider\", min:-20.0, max:20.0, step:0.1}\n",
"reverb_width = 1.0 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"reverb_freeze_mode = 0.0 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"\n",
"pitch_shift_semitones = 0.0 # @param {type:\"slider\", min:-12.0, max:12.0, step:0.1}\n",
"\n",
"limiter_threshold = -1.0 # @param {type:\"slider\", min:-20.0, max:0.0, step:0.1}\n",
"limiter_release_time = 0.05 # @param {type:\"slider\", min:0.0, max:1.0, step:0.01}\n",
"\n",
"gain_db = 0.0 # @param {type:\"slider\", min:-20.0, max:20.0, step:0.1}\n",
"\n",
"distortion_gain = 0.0 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"\n",
"chorus_rate = 1.5 # @param {type:\"slider\", min:0.1, max:10.0, step:0.1}\n",
"chorus_depth = 0.1 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"chorus_center_delay = 15.0 # @param {type:\"slider\", min:0.0, max:50.0, step:0.1}\n",
"chorus_feedback = 0.25 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"chorus_mix = 0.5 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"\n",
"bitcrush_bit_depth = 4 # @param {type:\"slider\", min:1, max:16, step:1}\n",
"\n",
"clipping_threshold = 0.5 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"\n",
"compressor_threshold = -20.0 # @param {type:\"slider\", min:-60.0, max:0.0, step:0.1}\n",
"compressor_ratio = 4.0 # @param {type:\"slider\", min:1.0, max:20.0, step:0.1}\n",
"compressor_attack = 0.001 # @param {type:\"slider\", min:0.0, max:0.1, step:0.001}\n",
"compressor_release = 0.1 # @param {type:\"slider\", min:0.0, max:1.0, step:0.01}\n",
"\n",
"delay_seconds = 0.1 # @param {type:\"slider\", min:0.0, max:1.0, step:0.01}\n",
"delay_feedback = 0.5 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"delay_mix = 0.5 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "1QkabnLlF2KB"
},
"source": [
"### **Train**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "64V5TWxp05cn"
},
"outputs": [],
"source": [
"# @title Setup model parameters\n",
"\n",
"model_name = \"Darwin\" # @param {type:\"string\"}\n",
"sample_rate = \"40k\" # @param [\"32k\", \"40k\", \"48k\"] {allow-input: false}\n",
"sr = int(sample_rate.rstrip(\"k\")) * 1000\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "oBzqm4JkGGa0"
},
"outputs": [],
"source": [
"# @title Preprocess Dataset\n",
"\n",
"dataset_path = \"/content/drive/MyDrive/Darwin_Dataset\" # @param {type:\"string\"}\n",
"\n",
"cut_preprocess = \"Automatic\" # @param [\"Skip\",\"Simple\",\"Automatic\"]\n",
"chunk_len = 3 # @param {type:\"slider\", min:0.5, max:5.0, step:0.5}\n",
"overlap_len = 0.3 # @param {type:\"slider\", min:0, max:0.5, step:0.1}\n",
"process_effects = False # @param{type:\"boolean\"}\n",
"noise_reduction = False # @param{type:\"boolean\"}\n",
"noise_reduction_strength = 0.7 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
"normalization_mode = \"none\" # @param [\"none\",\"pre\",\"post\"]\n",
"\n",
"%cd /content/Applio\n",
"!python core.py preprocess --model_name \"{model_name}\" --dataset_path \"{dataset_path}\" --sample_rate \"{sr}\" --cpu_cores \"{cpu_cores}\" --cut_preprocess \"{cut_preprocess}\" --process_effects \"{process_effects}\" --noise_reduction \"{noise_reduction}\" --noise_reduction_strength \"{noise_reduction_strength}\" --chunk_len \"{chunk_len}\" --overlap_len \"{overlap_len}\" --normalization_mode \"{normalization_mode}\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "zWMiMYfRJTJv"
},
"outputs": [],
"source": [
"# @title Extract Features\n",
"f0_method = \"rmvpe\" # @param [\"crepe\", \"crepe-tiny\", \"rmvpe\"] {allow-input: false}\n",
"\n",
"sr = int(sample_rate.rstrip(\"k\")) * 1000\n",
"include_mutes = 2 # @param {type:\"slider\", min:0, max:10, step:1}\n",
"embedder_model = \"contentvec\" # @param [\"contentvec\", \"chinese-hubert-base\", \"japanese-hubert-base\", \"korean-hubert-base\", \"custom\"] {allow-input: false}\n",
"embedder_model_custom = \"\" # @param {type:\"string\"}\n",
"\n",
"%cd /content/Applio\n",
"!python core.py extract --model_name \"{model_name}\" --f0_method \"{f0_method}\" --sample_rate \"{sr}\" --cpu_cores \"{cpu_cores}\" --gpu \"0\" --embedder_model \"{embedder_model}\" --embedder_model_custom \"{embedder_model_custom}\" --include_mutes \"{include_mutes}\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "bHLs5AT4Q1ck"
},
"outputs": [],
"source": [
"# @title Generate index file\n",
"index_algorithm = \"Auto\" # @param [\"Auto\", \"Faiss\", \"KMeans\"] {allow-input: false}\n",
"\n",
"%cd /content/Applio\n",
"!python core.py index --model_name \"{model_name}\" --index_algorithm \"{index_algorithm}\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "TI6LLdIzKAIa"
},
"outputs": [],
"source": [
"# @title Start Training\n",
"# @markdown ### ⚙️ Train Settings\n",
"total_epoch = 800 # @param {type:\"integer\"}\n",
"batch_size = 8 # @param {type:\"slider\", min:1, max:25, step:0}\n",
"pretrained = True # @param{type:\"boolean\"}\n",
"cleanup = False # @param{type:\"boolean\"}\n",
"cache_data_in_gpu = False # @param{type:\"boolean\"}\n",
"vocoder = \"HiFi-GAN\" # @param [\"HiFi-GAN\"]\n",
"checkpointing = False\n",
"tensorboard = True # @param{type:\"boolean\"}\n",
"# @markdown ### ➡️ Choose how many epochs your model will be stored\n",
"save_every_epoch = 10 # @param {type:\"slider\", min:1, max:100, step:0}\n",
"save_only_latest = True # @param{type:\"boolean\"}\n",
"save_every_weights = False # @param{type:\"boolean\"}\n",
"overtraining_detector = False # @param{type:\"boolean\"}\n",
"overtraining_threshold = 50 # @param {type:\"slider\", min:1, max:100, step:0}\n",
"# @markdown ### ❓ Optional\n",
"# @markdown In case you select custom pretrained, you will have to download the pretraineds and enter the path of the pretraineds.\n",
"custom_pretrained = False # @param{type:\"boolean\"}\n",
"g_pretrained_path = \"/content/Applio/rvc/models/pretraineds/pretraineds_custom/G48k.pth\" # @param {type:\"string\"}\n",
"d_pretrained_path = \"/content/Applio/rvc/models/pretraineds/pretraineds_custom/D48k.pth\" # @param {type:\"string\"}\n",
"\n",
"\n",
"%cd /content/Applio\n",
"if tensorboard:\n",
" %load_ext tensorboard\n",
" %tensorboard --logdir logs --bind_all\n",
"!python core.py train --model_name \"{model_name}\" --save_every_epoch \"{save_every_epoch}\" --save_only_latest \"{save_only_latest}\" --save_every_weights \"{save_every_weights}\" --total_epoch \"{total_epoch}\" --sample_rate \"{sr}\" --batch_size \"{batch_size}\" --gpu 0 --pretrained \"{pretrained}\" --custom_pretrained \"{custom_pretrained}\" --g_pretrained_path \"{g_pretrained_path}\" --d_pretrained_path \"{d_pretrained_path}\" --overtraining_detector \"{overtraining_detector}\" --overtraining_threshold \"{overtraining_threshold}\" --cleanup \"{cleanup}\" --cache_data_in_gpu \"{cache_data_in_gpu}\" --vocoder \"{vocoder}\" --checkpointing \"{checkpointing}\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "X_eU_SoiHIQg"
},
"outputs": [],
"source": [
"# @title Export model\n",
"# @markdown Export model to a zip file\n",
"# @markdown * Training: Bigger file size, can continue training\n",
"# @markdown * Inference: Smaller file size, only for model inference\n",
"# @title\n",
"# @markdown (Note) Exporting for training is only recommended for use outside of Applio, if you plan to resume training later, use [Sync with Google Drive](#scrollTo=2miFQtlfiWy_) cell instead.\n",
"EXPORT_PATH = \"/content/drive/MyDrive/ApplioExported\"\n",
"from pathlib import Path\n",
"\n",
"export_for = \"inference\" # @param [\"training\", \"inference\"] {allow-input: false}\n",
"\n",
"logs_folder = Path(f\"/content/Applio/logs/{model_name}/\")\n",
"if not (logs_folder.exists() and logs_folder.is_dir()):\n",
" raise FileNotFoundError(f\"{model_name} model folder not found\")\n",
"\n",
"%cd {logs_folder}/..\n",
"if export_for == \"training\":\n",
" !zip -r \"/content/{model_name}.zip\" \"{model_name}\"\n",
"else:\n",
" # find latest trained weight file\n",
" !ls -t \"{model_name}/{model_name}\"_*e_*s.pth | head -n 1 > /tmp/weight.txt\n",
" weight_path = open(\"/tmp/weight.txt\", \"r\").read().strip()\n",
" if weight_path == \"\":\n",
" raise FileNotFoundError(\"Model has no weight file, please finish training first\")\n",
" weight_name = Path(weight_path).name\n",
" # command does not fail if index is missing, this is intended\n",
" !zip \"/content/{model_name}.zip\" \"{model_name}/{weight_name}\" \"{model_name}/{model_name}.index\"\n",
"\n",
"if Path(\"/content/drive\").is_mount():\n",
" !mkdir -p \"{EXPORT_PATH}\"\n",
" !mv \"/content/{model_name}.zip\" \"{EXPORT_PATH}\" && echo \"Exported model to {EXPORT_PATH}/{model_name}.zip\"\n",
"else:\n",
" !echo \"Drive not mounted, exporting model to /content/{model_name}.zip\""
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [
"ymMCTSD6m8qV"
],
"private_outputs": true,
"provenance": [],
"toc_visible": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|