File size: 44,916 Bytes
06c6114 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "Qpw04rkbynx0"
},
"source": [
"To run this, press \"*Runtime*\" and press \"*Run all*\" on a **free** Tesla T4 Google Colab instance!\n",
"<div class=\"align-center\">\n",
"<a href=\"https://unsloth.ai/\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png\" width=\"115\"></a>\n",
"<a href=\"https://discord.gg/unsloth\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/Discord button.png\" width=\"145\"></a>\n",
"<a href=\"https://docs.unsloth.ai/\"><img src=\"https://github.com/unslothai/unsloth/blob/main/images/documentation%20green%20button.png?raw=true\" width=\"125\"></a></a> Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/unslothai/unsloth\">Github</a> </i> ⭐\n",
"</div>\n",
"\n",
"To install Unsloth on your own computer, follow the installation instructions on our Github page [here](https://docs.unsloth.ai/get-started/installing-+-updating).\n",
"\n",
"You will learn how to do [data prep](#Data), how to [train](#Train), how to [run the model](#Inference), & [how to save it](#Save)\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "5fs-yYEaynx1"
},
"source": [
"### News"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "pyJK0UZaynx2"
},
"source": [
"Unsloth now supports Text-to-Speech (TTS) models. Read our [guide here](https://docs.unsloth.ai/basics/text-to-speech-tts-fine-tuning).\n",
"\n",
"Read our **[Gemma 3N Guide](https://docs.unsloth.ai/basics/gemma-3n-how-to-run-and-fine-tune)** and check out our new **[Dynamic 2.0](https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs)** quants which outperforms other quantization methods!\n",
"\n",
"Visit our docs for all our [model uploads](https://docs.unsloth.ai/get-started/all-our-models) and [notebooks](https://docs.unsloth.ai/get-started/unsloth-notebooks).\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "SDUHv0mwynx3"
},
"source": [
"### Installation"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "MY4G3EIbynx3"
},
"outputs": [],
"source": [
"%%capture\n",
"import os\n",
"if \"COLAB_\" not in \"\".join(os.environ.keys()):\n",
" %pip install unsloth\n",
"else:\n",
" # Do this only in Colab notebooks! Otherwise use pip install unsloth\n",
" %pip install --no-deps bitsandbytes accelerate xformers==0.0.29.post3 peft trl triton cut_cross_entropy unsloth_zoo\n",
" %pip install sentencepiece protobuf \"datasets>=3.4.1,<4.0.0\" \"huggingface_hub>=0.34.0\" hf_transfer\n",
" %pip install --no-deps unsloth\n",
"%git clone https://github.com/SparkAudio/Spark-TTS\n",
"%pip install omegaconf einx"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "AkWYsztAs9Ky"
},
"source": [
"### Unsloth\n",
"\n",
"`FastModel` supports loading nearly any model now! This includes Vision and Text models!\n",
"\n",
"Thank you to [Etherl](https://huggingface.co/Etherll) for creating this notebook!"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"execution": {
"iopub.execute_input": "2025-03-22T00:48:54.511089Z",
"iopub.status.busy": "2025-03-22T00:48:54.510770Z",
"iopub.status.idle": "2025-03-22T00:51:37.363415Z",
"shell.execute_reply": "2025-03-22T00:51:37.362696Z",
"shell.execute_reply.started": "2025-03-22T00:48:54.511053Z"
},
"id": "QmUBVEnvCDJv",
"outputId": "42083a68-d3cc-48c9-d852-b60796377434"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
"🦥 Unsloth Zoo will now patch everything to make training faster!\n",
"==((====))== Unsloth 2025.8.1: Fast Qwen2 patching. Transformers: 4.54.1.\n",
" \\\\ /| Tesla T4. Num GPUs = 1. Max memory: 14.741 GB. Platform: Linux.\n",
"O^O/ \\_/ \\ Torch: 2.6.0+cu124. CUDA: 7.5. CUDA Toolkit: 12.4. Triton: 3.2.0\n",
"\\ / Bfloat16 = FALSE. FA [Xformers = 0.0.29.post3. FA2 = False]\n",
" \"-____-\" Free license: http://github.com/unslothai/unsloth\n",
"Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n",
"Unsloth: Float16 full finetuning uses more memory since we upcast weights to float32.\n"
]
}
],
"source": [
"from unsloth import FastModel\n",
"import torch\n",
"from huggingface_hub import snapshot_download\n",
"\n",
"max_seq_length = 2048 # Choose any for long context!\n",
"\n",
"fourbit_models = [\n",
" # 4bit dynamic quants for superior accuracy and low memory use\n",
" \"unsloth/gemma-3-4b-it-unsloth-bnb-4bit\",\n",
" \"unsloth/gemma-3-12b-it-unsloth-bnb-4bit\",\n",
" \"unsloth/gemma-3-27b-it-unsloth-bnb-4bit\",\n",
" # Qwen3 new models\n",
" \"unsloth/Qwen3-4B-unsloth-bnb-4bit\",\n",
" \"unsloth/Qwen3-8B-unsloth-bnb-4bit\",\n",
" # Other very popular models!\n",
" \"unsloth/Llama-3.1-8B\",\n",
" \"unsloth/Llama-3.2-3B\",\n",
" \"unsloth/Llama-3.3-70B\",\n",
" \"unsloth/mistral-7b-instruct-v0.3\",\n",
" \"unsloth/Phi-4\",\n",
"] # More models at https://huggingface.co/unsloth\n",
"\n",
"# Download model and code\n",
"snapshot_download(\"unsloth/Spark-TTS-0.5B\", local_dir = \"Spark-TTS-0.5B\")\n",
"\n",
"model, tokenizer = FastModel.from_pretrained(\n",
" model_name = f\"Spark-TTS-0.5B/LLM\",\n",
" max_seq_length = max_seq_length,\n",
" dtype = torch.float32, # Spark seems to only work on float32 for now\n",
" full_finetuning = True, # We support full finetuning now!\n",
" load_in_4bit = False,\n",
" #token = \"hf_...\", # use one if using gated models like meta-llama/Llama-2-7b-hf\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "SXd9bTZd1aaL"
},
"source": [
"We now add LoRA adapters so we only need to update 1 to 10% of all parameters!"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"execution": {
"iopub.execute_input": "2025-03-22T00:51:37.365079Z",
"iopub.status.busy": "2025-03-22T00:51:37.364731Z",
"iopub.status.idle": "2025-03-22T00:51:44.221612Z",
"shell.execute_reply": "2025-03-22T00:51:44.220949Z",
"shell.execute_reply.started": "2025-03-22T00:51:37.365045Z"
},
"id": "6bZsfBuZDeCL",
"outputId": "292447b8-fd80-4b8b-ba3f-4637a1045166"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Unsloth: Full finetuning is enabled, so .get_peft_model has no effect\n"
]
}
],
"source": [
"#LoRA does not work with float32 only works with bfloat16 !!!\n",
"model = FastModel.get_peft_model(\n",
" model,\n",
" r = 128, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128\n",
" target_modules = [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n",
" \"gate_proj\", \"up_proj\", \"down_proj\",],\n",
" lora_alpha = 128,\n",
" lora_dropout = 0, # Supports any, but = 0 is optimized\n",
" bias = \"none\", # Supports any, but = \"none\" is optimized\n",
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vITh0KVJ10qX"
},
"source": [
"<a name=\"Data\"></a>\n",
"### Data Prep \n",
"\n",
"We will use the `MrDragonFox/Elise`, which is designed for training TTS models. Ensure that your dataset follows the required format: **text, audio** for single-speaker models or **source, text, audio** for multi-speaker models. You can modify this section to accommodate your own dataset, but maintaining the correct structure is essential for optimal training."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"execution": {
"iopub.execute_input": "2025-03-22T00:51:44.222880Z",
"iopub.status.busy": "2025-03-22T00:51:44.222617Z",
"iopub.status.idle": "2025-03-22T00:52:16.516878Z",
"shell.execute_reply": "2025-03-22T00:52:16.516033Z",
"shell.execute_reply.started": "2025-03-22T00:51:44.222848Z"
},
"id": "LjY75GoYUCB8"
},
"outputs": [],
"source": [
"from datasets import load_dataset\n",
"dataset = load_dataset(\"Balaji-1904/TTS_KN_DS_V1.1\", split = \"train\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 173,
"referenced_widgets": [
"a3b0c0581f1f4c428baaadd8e9a39b6f",
"2315228ff2b141afabe1263471f5364b",
"0474debc340943bd85f3daf92aebf7aa",
"cff1b0fa2ea24f45aab26685353eefdd",
"b7e20be79df246f19b35114a690e44f0",
"426eb100a94642f79e6b99777406a265",
"a36b5cf197dd4bd9a7f70aa6671b804c",
"0de4d0f282404edfbc191dca73f15f35",
"e58b5ad2f781475d8af2ddb38009baa6",
"33fbacbb2aa146cd90586357eec1dc3e",
"930b4d1d5f4b494b830df4d4c398e67c"
]
},
"execution": {
"iopub.execute_input": "2025-03-22T00:52:16.518175Z",
"iopub.status.busy": "2025-03-22T00:52:16.517841Z",
"iopub.status.idle": "2025-03-22T00:52:35.039329Z",
"shell.execute_reply": "2025-03-22T00:52:35.038356Z",
"shell.execute_reply.started": "2025-03-22T00:52:16.518146Z"
},
"id": "zK94B-Pfioto",
"outputId": "3f11cf35-c173-410d-f709-43552323f26f"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/usr/local/lib/python3.11/dist-packages/torch/nn/utils/weight_norm.py:143: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.\n",
" WeightNorm.apply(module, name, dim)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Missing tensor: mel_transformer.spectrogram.window\n",
"Missing tensor: mel_transformer.mel_scale.fb\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Parameter 'function'=<function formatting_audio_func at 0x7bd438943100> of the transform datasets.arrow_dataset.Dataset._map_single couldn't be hashed properly, a random hash was used instead. Make sure your transforms and parameters are serializable with pickle or dill for the dataset fingerprinting and caching to work. If you reuse this transform, the caching mechanism will consider it to be different from the previous calls and recompute everything. This warning is only showed once. Subsequent hashing failures won't be showed.\n",
"WARNING:datasets.fingerprint:Parameter 'function'=<function formatting_audio_func at 0x7bd438943100> of the transform datasets.arrow_dataset.Dataset._map_single couldn't be hashed properly, a random hash was used instead. Make sure your transforms and parameters are serializable with pickle or dill for the dataset fingerprinting and caching to work. If you reuse this transform, the caching mechanism will consider it to be different from the previous calls and recompute everything. This warning is only showed once. Subsequent hashing failures won't be showed.\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a3b0c0581f1f4c428baaadd8e9a39b6f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/401 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#@title Tokenization Function\n",
"\n",
"import locale\n",
"import torchaudio.transforms as T\n",
"import os\n",
"import torch\n",
"import sys\n",
"import numpy as np\n",
"sys.path.append('Spark-TTS')\n",
"from sparktts.models.audio_tokenizer import BiCodecTokenizer\n",
"from sparktts.utils.audio import audio_volume_normalize\n",
"\n",
"audio_tokenizer = BiCodecTokenizer(\"Spark-TTS-0.5B\", \"cuda\")\n",
"def extract_wav2vec2_features( wavs: torch.Tensor) -> torch.Tensor:\n",
" \"\"\"extract wav2vec2 features\"\"\"\n",
"\n",
" if wavs.shape[0] != 1:\n",
"\n",
" raise ValueError(f\"Expected batch size 1, but got shape {wavs.shape}\")\n",
" wav_np = wavs.squeeze(0).cpu().numpy()\n",
"\n",
" processed = audio_tokenizer.processor(\n",
" wav_np,\n",
" sampling_rate=16000,\n",
" return_tensors=\"pt\",\n",
" padding=True,\n",
" )\n",
" input_values = processed.input_values\n",
"\n",
" input_values = input_values.to(audio_tokenizer.feature_extractor.device)\n",
"\n",
" model_output = audio_tokenizer.feature_extractor(\n",
" input_values,\n",
" )\n",
"\n",
"\n",
" if model_output.hidden_states is None:\n",
" raise ValueError(\"Wav2Vec2Model did not return hidden states. Ensure config `output_hidden_states=True`.\")\n",
"\n",
" num_layers = len(model_output.hidden_states)\n",
" required_layers = [11, 14, 16]\n",
" if any(l >= num_layers for l in required_layers):\n",
" raise IndexError(f\"Requested hidden state indices {required_layers} out of range for model with {num_layers} layers.\")\n",
"\n",
" feats_mix = (\n",
" model_output.hidden_states[11] + model_output.hidden_states[14] + model_output.hidden_states[16]\n",
" ) / 3\n",
"\n",
" return feats_mix\n",
"def formatting_audio_func(example):\n",
" text = f\"{example['source']}: {example['text']}\" if \"source\" in example else example[\"text\"]\n",
" audio_array = example[\"audio\"][\"array\"]\n",
" sampling_rate = example[\"audio\"][\"sampling_rate\"]\n",
"\n",
" target_sr = audio_tokenizer.config['sample_rate']\n",
"\n",
" if sampling_rate != target_sr:\n",
" resampler = T.Resample(orig_freq=sampling_rate, new_freq=target_sr)\n",
" audio_tensor_temp = torch.from_numpy(audio_array).float()\n",
" audio_array = resampler(audio_tensor_temp).numpy()\n",
"\n",
" if audio_tokenizer.config[\"volume_normalize\"]:\n",
" audio_array = audio_volume_normalize(audio_array)\n",
"\n",
" ref_wav_np = audio_tokenizer.get_ref_clip(audio_array)\n",
"\n",
" audio_tensor = torch.from_numpy(audio_array).unsqueeze(0).float().to(audio_tokenizer.device)\n",
" ref_wav_tensor = torch.from_numpy(ref_wav_np).unsqueeze(0).float().to(audio_tokenizer.device)\n",
"\n",
"\n",
" feat = extract_wav2vec2_features(audio_tensor)\n",
"\n",
" batch = {\n",
"\n",
" \"wav\": audio_tensor,\n",
" \"ref_wav\": ref_wav_tensor,\n",
" \"feat\": feat.to(audio_tokenizer.device),\n",
" }\n",
"\n",
"\n",
" semantic_token_ids, global_token_ids = audio_tokenizer.model.tokenize(batch)\n",
"\n",
" global_tokens = \"\".join(\n",
" [f\"<|bicodec_global_{i}|>\" for i in global_token_ids.squeeze().cpu().numpy()] # Squeeze batch dim\n",
" )\n",
" semantic_tokens = \"\".join(\n",
" [f\"<|bicodec_semantic_{i}|>\" for i in semantic_token_ids.squeeze().cpu().numpy()] # Squeeze batch dim\n",
" )\n",
"\n",
" inputs = [\n",
" \"<|task_tts|>\",\n",
" \"<|start_content|>\",\n",
" text,\n",
" \"<|end_content|>\",\n",
" \"<|start_global_token|>\",\n",
" global_tokens,\n",
" \"<|end_global_token|>\",\n",
" \"<|start_semantic_token|>\",\n",
" semantic_tokens,\n",
" \"<|end_semantic_token|>\",\n",
" \"<|im_end|>\"\n",
" ]\n",
" inputs = \"\".join(inputs)\n",
" return {\"text\": inputs}\n",
"\n",
"\n",
"dataset = dataset.map(formatting_audio_func, remove_columns=[\"audio\"])\n",
"print(\"Moving Bicodec model and Wav2Vec2Model to cpu.\")\n",
"audio_tokenizer.model.cpu()\n",
"audio_tokenizer.feature_extractor.cpu()\n",
"torch.cuda.empty_cache()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "idAEIeSQ3xdS"
},
"source": [
"<a name=\"Train\"></a>\n",
"### Train the model\n",
"Now let's use Huggingface TRL's `SFTTrainer`! More docs here: [TRL SFT docs](https://huggingface.co/docs/trl/sft_trainer). We do 60 steps to speed things up, but you can set `num_train_epochs=1` for a full run, and turn off `max_steps=None`. We also support TRL's `DPOTrainer`!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2025-03-22T00:34:09.688959Z",
"iopub.status.busy": "2025-03-22T00:34:09.688649Z",
"iopub.status.idle": "2025-03-22T00:34:09.729661Z",
"shell.execute_reply": "2025-03-22T00:34:09.729001Z",
"shell.execute_reply.started": "2025-03-22T00:34:09.688939Z"
},
"id": "95_Nn-89DhsL"
},
"outputs": [],
"source": [
"from trl import SFTConfig, SFTTrainer\n",
"trainer = SFTTrainer(\n",
" model = model,\n",
" tokenizer = tokenizer,\n",
" train_dataset = dataset,\n",
" dataset_text_field = \"text\",\n",
" max_seq_length = max_seq_length,\n",
" packing = False, # Can make training 5x faster for short sequences.\n",
" args = SFTConfig(\n",
" per_device_train_batch_size = 2,\n",
" gradient_accumulation_steps = 4,\n",
" warmup_steps = 5,\n",
" num_train_epochs = 5, # Set this for 1 full training run.\n",
" #max_steps = 60,\n",
" learning_rate = 2e-4,\n",
" fp16 = False, # We're doing full float32 s disable mixed precision\n",
" bf16 = False, # We're doing full float32 s disable mixed precision\n",
" logging_steps = 1,\n",
" optim = \"adamw_8bit\",\n",
" weight_decay = 0.01,\n",
" lr_scheduler_type = \"linear\",\n",
" seed = 3407,\n",
" output_dir = \"outputs\",\n",
" report_to = \"tensorboard\", # Use this for WandB etc\n",
" ),\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "2ejIt2xSNKKp"
},
"outputs": [],
"source": [
"# @title Show current memory stats\n",
"gpu_stats = torch.cuda.get_device_properties(0)\n",
"start_gpu_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)\n",
"max_memory = round(gpu_stats.total_memory / 1024 / 1024 / 1024, 3)\n",
"print(f\"GPU = {gpu_stats.name}. Max memory = {max_memory} GB.\")\n",
"print(f\"{start_gpu_memory} GB of memory reserved.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2025-03-22T00:34:12.049152Z",
"iopub.status.busy": "2025-03-22T00:34:12.048862Z",
"iopub.status.idle": "2025-03-22T00:34:14.404349Z",
"shell.execute_reply": "2025-03-22T00:34:14.403239Z",
"shell.execute_reply.started": "2025-03-22T00:34:12.049130Z"
},
"id": "yqxqAZ7KJ4oL"
},
"outputs": [],
"source": [
"trainer_stats = trainer.train()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "pCqnaKmlO1U9"
},
"outputs": [],
"source": [
"# @title Show final memory and time stats\n",
"used_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)\n",
"used_memory_for_lora = round(used_memory - start_gpu_memory, 3)\n",
"used_percentage = round(used_memory / max_memory * 100, 3)\n",
"lora_percentage = round(used_memory_for_lora / max_memory * 100, 3)\n",
"print(f\"{trainer_stats.metrics['train_runtime']} seconds used for training.\")\n",
"print(\n",
" f\"{round(trainer_stats.metrics['train_runtime']/60, 2)} minutes used for training.\"\n",
")\n",
"print(f\"Peak reserved memory = {used_memory} GB.\")\n",
"print(f\"Peak reserved memory for training = {used_memory_for_lora} GB.\")\n",
"print(f\"Peak reserved memory % of max memory = {used_percentage} %.\")\n",
"print(f\"Peak reserved memory for training % of max memory = {lora_percentage} %.\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ekOmTR1hSNcr"
},
"source": [
"<a name=\"Inference\"></a>\n",
"### Inference\n",
"Let's run the model! You can change the prompts\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "apUdB40Ep6Ki"
},
"outputs": [],
"source": [
"input_text = \"Hey there my name is Elise, <giggles> and I'm a speech generation model that can sound like a person.\"\n",
"\n",
"chosen_voice = None # None for single-speaker"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"execution": {
"iopub.execute_input": "2025-03-22T00:52:35.040842Z",
"iopub.status.busy": "2025-03-22T00:52:35.040125Z",
"iopub.status.idle": "2025-03-22T00:52:35.050560Z",
"shell.execute_reply": "2025-03-22T00:52:35.049663Z",
"shell.execute_reply.started": "2025-03-22T00:52:35.040818Z"
},
"id": "krYI8PrRJ6MX"
},
"outputs": [],
"source": [
"#@title Run Inference\n",
"\n",
"import torch\n",
"import re\n",
"import numpy as np\n",
"from typing import Dict, Any\n",
"import torchaudio.transforms as T\n",
"\n",
"FastModel.for_inference(model) # Enable native 2x faster inference\n",
"\n",
"@torch.inference_mode()\n",
"def generate_speech_from_text(\n",
" text: str,\n",
" temperature: float = 0.8, # Generation temperature\n",
" top_k: int = 50, # Generation top_k\n",
" top_p: float = 1, # Generation top_p\n",
" max_new_audio_tokens: int = 2048, # Max tokens for audio part\n",
" device: torch.device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
") -> np.ndarray:\n",
" \"\"\"\n",
" Generates speech audio from text using default voice control parameters.\n",
"\n",
" Args:\n",
" text (str): The text input to be converted to speech.\n",
" temperature (float): Sampling temperature for generation.\n",
" top_k (int): Top-k sampling parameter.\n",
" top_p (float): Top-p (nucleus) sampling parameter.\n",
" max_new_audio_tokens (int): Max number of new tokens to generate (limits audio length).\n",
" device (torch.device): Device to run inference on.\n",
"\n",
" Returns:\n",
" np.ndarray: Generated waveform as a NumPy array.\n",
" \"\"\"\n",
"\n",
" torch.compiler.reset()\n",
"\n",
" prompt = \"\".join([\n",
" \"<|task_tts|>\",\n",
" \"<|start_content|>\",\n",
" text,\n",
" \"<|end_content|>\",\n",
" \"<|start_global_token|>\"\n",
" ])\n",
"\n",
" model_inputs = tokenizer([prompt], return_tensors=\"pt\").to(device)\n",
"\n",
" print(\"Generating token sequence...\")\n",
" generated_ids = model.generate(\n",
" **model_inputs,\n",
" max_new_tokens=max_new_audio_tokens, # Limit generation length\n",
" do_sample=True,\n",
" temperature=temperature,\n",
" top_k=top_k,\n",
" top_p=top_p,\n",
" eos_token_id=tokenizer.eos_token_id, # Stop token\n",
" pad_token_id=tokenizer.pad_token_id # Use models pad token id\n",
" )\n",
" print(\"Token sequence generated.\")\n",
"\n",
"\n",
" generated_ids_trimmed = generated_ids[:, model_inputs.input_ids.shape[1]:]\n",
"\n",
"\n",
" predicts_text = tokenizer.batch_decode(generated_ids_trimmed, skip_special_tokens=False)[0]\n",
" # print(f\"\\nGenerated Text (for parsing):\\n{predicts_text}\\n\") # Debugging\n",
"\n",
" # Extract semantic token IDs using regex\n",
" semantic_matches = re.findall(r\"<\\|bicodec_semantic_(\\d+)\\|>\", predicts_text)\n",
" if not semantic_matches:\n",
" print(\"Warning: No semantic tokens found in the generated output.\")\n",
" # Handle appropriately - perhaps return silence or raise error\n",
" return np.array([], dtype=np.float32)\n",
"\n",
" pred_semantic_ids = torch.tensor([int(token) for token in semantic_matches]).long().unsqueeze(0) # Add batch dim\n",
"\n",
" # Extract global token IDs using regex (assuming controllable mode also generates these)\n",
" global_matches = re.findall(r\"<\\|bicodec_global_(\\d+)\\|>\", predicts_text)\n",
" if not global_matches:\n",
" print(\"Warning: No global tokens found in the generated output (controllable mode). Might use defaults or fail.\")\n",
" pred_global_ids = torch.zeros((1, 1), dtype=torch.long)\n",
" else:\n",
" pred_global_ids = torch.tensor([int(token) for token in global_matches]).long().unsqueeze(0) # Add batch dim\n",
"\n",
" pred_global_ids = pred_global_ids.unsqueeze(0) # Shape becomes (1, 1, N_global)\n",
"\n",
" print(f\"Found {pred_semantic_ids.shape[1]} semantic tokens.\")\n",
" print(f\"Found {pred_global_ids.shape[2]} global tokens.\")\n",
"\n",
"\n",
" # 5. Detokenize using BiCodecTokenizer\n",
" print(\"Detokenizing audio tokens...\")\n",
" # Ensure audio_tokenizer and its internal model are on the correct device\n",
" audio_tokenizer.device = device\n",
" audio_tokenizer.model.to(device)\n",
" # Squeeze the extra dimension from global tokens as seen in SparkTTS example\n",
" wav_np = audio_tokenizer.detokenize(\n",
" pred_global_ids.to(device).squeeze(0), # Shape (1, N_global)\n",
" pred_semantic_ids.to(device) # Shape (1, N_semantic)\n",
" )\n",
" print(\"Detokenization complete.\")\n",
"\n",
" return wav_np\n",
"\n",
"if __name__ == \"__main__\":\n",
" print(f\"Generating speech for: '{input_text}'\")\n",
" text = f\"{chosen_voice}: \" + input_text if chosen_voice else input_text\n",
" generated_waveform = generate_speech_from_text(input_text)\n",
"\n",
" if generated_waveform.size > 0:\n",
" import soundfile as sf\n",
" output_filename = \"generated_speech_controllable.wav\"\n",
" sample_rate = audio_tokenizer.config.get(\"sample_rate\", 16000)\n",
" sf.write(output_filename, generated_waveform, sample_rate)\n",
" print(f\"Audio saved to {output_filename}\")\n",
"\n",
" # Optional: Play in notebook\n",
" from IPython.display import Audio, display\n",
" display(Audio(generated_waveform, rate=sample_rate))\n",
" else:\n",
" print(\"Audio generation failed (no tokens found?).\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "uMuVrWbjAzhc"
},
"source": [
"<a name=\"Save\"></a>\n",
"### Saving, loading finetuned models\n",
"To save the final model as LoRA adapters, either use Huggingface's `push_to_hub` for an online save or `save_pretrained` for a local save.\n",
"\n",
"**[NOTE]** This ONLY saves the LoRA adapters, and not the full model. To save to 16bit or GGUF, scroll down!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "upcOlWe7A1vc"
},
"outputs": [],
"source": [
"model.save_pretrained(\"lora_model\") # Local saving\n",
"tokenizer.save_pretrained(\"lora_model\")\n",
"# model.push_to_hub(\"your_name/lora_model\", token = \"...\") # Online saving\n",
"# tokenizer.push_to_hub(\"your_name/lora_model\", token = \"...\") # Online saving"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "f422JgM9sdVT"
},
"source": [
"\n",
"### Saving to float16\n",
"\n",
"We also support saving to `float16` directly. Select `merged_16bit` for float16 or `merged_4bit` for int4. We also allow `lora` adapters as a fallback. Use `push_to_hub_merged` to upload to your Hugging Face account! You can go to https://huggingface.co/settings/tokens for your personal tokens."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "iHjt_SMYsd3P",
"outputId": "bd8cccb7-6b95-45bf-80da-de120988447e"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Unsloth: You have 1 CPUs. Using `safe_serialization` is 10x slower.\n",
"We shall switch to Pytorch saving, which might take 3 minutes and not 30 minutes.\n",
"To force `safe_serialization`, set it to `None` instead.\n",
"Unsloth: Kaggle/Colab has limited disk space. We need to delete the downloaded\n",
"model which will save 4-16GB of disk space, allowing you to save on Kaggle/Colab.\n",
"Unsloth: Will remove a cached repo with size 15.1G\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Unsloth: Merging 4bit and LoRA weights to 16bit...\n",
"Unsloth: Will use up to 3.99 out of 12.67 RAM for saving.\n",
"Unsloth: Saving model... This might take 5 minutes ...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 28/28 [00:01<00:00, 27.83it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Unsloth: Saving tokenizer... Done.\n",
"Unsloth: Saving model/pytorch_model-00001-of-00002.bin...\n",
"Unsloth: Saving model/pytorch_model-00002-of-00002.bin...\n",
"Done.\n"
]
}
],
"source": [
"# Merge to 16bit\n",
"if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_16bit\",)\n",
"if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_16bit\", token = \"\")\n",
"\n",
"# Merge to 4bit\n",
"if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_4bit\",)\n",
"if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_4bit\", token = \"\")\n",
"\n",
"# Just LoRA adapters\n",
"if False:\n",
" model.save_pretrained(\"model\")\n",
" tokenizer.save_pretrained(\"model\")\n",
"if False:\n",
" model.push_to_hub(\"hf/model\", token = \"\")\n",
" tokenizer.push_to_hub(\"hf/model\", token = \"\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "egOSE7Cgynx7"
},
"source": [
"And we're done! If you have any questions on Unsloth, we have a [Discord](https://discord.gg/unsloth) channel! If you find any bugs or want to keep updated with the latest LLM stuff, or need help, join projects etc, feel free to join our Discord!\n",
"\n",
"Some other links:\n",
"1. Train your own reasoning model - Llama GRPO notebook [Free Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-GRPO.ipynb)\n",
"2. Saving finetunes to Ollama. [Free notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-Ollama.ipynb)\n",
"3. Llama 3.2 Vision finetuning - Radiography use case. [Free Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)\n",
"6. See notebooks for DPO, ORPO, Continued pretraining, conversational finetuning and more on our [documentation](https://docs.unsloth.ai/get-started/unsloth-notebooks)!\n",
"\n",
"<div class=\"align-center\">\n",
" <a href=\"https://unsloth.ai\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png\" width=\"115\"></a>\n",
" <a href=\"https://discord.gg/unsloth\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/Discord.png\" width=\"145\"></a>\n",
" <a href=\"https://docs.unsloth.ai/\"><img src=\"https://github.com/unslothai/unsloth/blob/main/images/documentation%20green%20button.png?raw=true\" width=\"125\"></a>\n",
"\n",
" Join Discord if you need help + ⭐️ <i>Star us on <a href=\"https://github.com/unslothai/unsloth\">Github</a> </i> ⭐️\n",
"</div>\n"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": []
},
"kaggle": {
"accelerator": "nvidiaTeslaT4",
"dataSources": [],
"dockerImageVersionId": 30919,
"isGpuEnabled": true,
"isInternetEnabled": true,
"language": "python",
"sourceType": "notebook"
},
"kernelspec": {
"display_name": "TTS_ft",
"language": "python",
"name": "tts_ft"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"0474debc340943bd85f3daf92aebf7aa": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_0de4d0f282404edfbc191dca73f15f35",
"max": 401,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_e58b5ad2f781475d8af2ddb38009baa6",
"value": 354
}
},
"0de4d0f282404edfbc191dca73f15f35": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"2315228ff2b141afabe1263471f5364b": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_426eb100a94642f79e6b99777406a265",
"placeholder": "",
"style": "IPY_MODEL_a36b5cf197dd4bd9a7f70aa6671b804c",
"value": "Map: 88%"
}
},
"33fbacbb2aa146cd90586357eec1dc3e": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"426eb100a94642f79e6b99777406a265": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"930b4d1d5f4b494b830df4d4c398e67c": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"a36b5cf197dd4bd9a7f70aa6671b804c": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"a3b0c0581f1f4c428baaadd8e9a39b6f": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_2315228ff2b141afabe1263471f5364b",
"IPY_MODEL_0474debc340943bd85f3daf92aebf7aa",
"IPY_MODEL_cff1b0fa2ea24f45aab26685353eefdd"
],
"layout": "IPY_MODEL_b7e20be79df246f19b35114a690e44f0"
}
},
"b7e20be79df246f19b35114a690e44f0": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"cff1b0fa2ea24f45aab26685353eefdd": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_33fbacbb2aa146cd90586357eec1dc3e",
"placeholder": "",
"style": "IPY_MODEL_930b4d1d5f4b494b830df4d4c398e67c",
"value": " 354/401 [03:01<00:22, 2.11 examples/s]"
}
},
"e58b5ad2f781475d8af2ddb38009baa6": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
}
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|