File size: 41,195 Bytes
674fbd3 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "c219841f-493c-40f9-a6c9-3700f0c525d0",
"metadata": {},
"source": [
"# PEFT 库 LoRA 实战 - OpenAI Whisper-large-v2\n",
"\n",
"本教程使用 LoRA 在`OpenAI Whisper-large-v2`模型上实现`语音识别(ASR)`任务的微调训练。\n",
"\n",
"我们还结合了`int8` 量化进一步降低训练过程资源开销，同时保证了精度几乎不受影响。"
]
},
{
"cell_type": "markdown",
"id": "6d0a1e23-ea71-45d6-82d6-453077cf2d29",
"metadata": {},
"source": [
"## 全局参数设置"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "19d11aa3-9a73-4ce9-b6c5-a65a2fcb07c3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import os\n",
"os.environ[\"CUDA_DEVICE_ORDER\"]=\"PCI_BUS_ID\" # see issue #152\n",
"os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"2\"\n",
"\n",
"import torch\n",
"torch.cuda.device_count()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "ccd00402-d821-485e-8703-fb16bcb56a9e",
"metadata": {},
"outputs": [],
"source": [
"model_name_or_path = \"openai/whisper-large-v2\"\n",
"language = \"Chinese (China)\"\n",
"language_abbr = \"zh-CN\"\n",
"task = \"transcribe\"\n",
"dataset_name = \"mozilla-foundation/common_voice_11_0\"\n",
"\n",
"batch_size=64"
]
},
{
"cell_type": "markdown",
"id": "cfffa1df-e51e-4026-9817-1cebddf0061a",
"metadata": {},
"source": [
"## 下载数据集 Common Voice\n",
"\n",
"Common Voice 11.0 数据集包含许多不同语言的录音，总时长达数小时。\n",
"\n",
"本教程以中文数据为例，展示如何使用 LoRA 在 Whisper-large-v2 上进行微调训练。\n",
"\n",
"首先，初始化一个DatasetDict结构，并将训练集（将训练+验证拆分为训练集）和测试集拆分好，按照中文数据集构建配置加载到内存中："
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "21ff42f4-f3ec-46d3-b0c0-dd9ffbf7b50b",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"{'client_id': '95368aab163e0387e4fd4991b4f2d8ccfbd4364bf656c860230501fd27dcedf087773e4695a6cf5de9c4f1d406d582283190d065cdfa36b0e2b060cffaca977e',\n",
" 'path': '/store/jxzhang/.cache/huggingface/datasets/downloads/extracted/edf8cf7fef3457433a3a59929c4c4809972172377467a8f189ac185f3d5e4b53/zh-CN_train_0/common_voice_zh-CN_33211332.mp3',\n",
" 'audio': {'path': '/store/jxzhang/.cache/huggingface/datasets/downloads/extracted/edf8cf7fef3457433a3a59929c4c4809972172377467a8f189ac185f3d5e4b53/zh-CN_train_0/common_voice_zh-CN_33211332.mp3',\n",
" 'array': array([-6.82121026e-13, -2.27373675e-12, -2.27373675e-12, ...,\n",
" 1.21667399e-05, 3.23003678e-06, -2.43066324e-07]),\n",
" 'sampling_rate': 48000},\n",
" 'sentence': '性喜温暖润湿气候且耐寒。',\n",
" 'up_votes': 2,\n",
" 'down_votes': 0,\n",
" 'age': '',\n",
" 'gender': '',\n",
" 'accent': '',\n",
" 'locale': 'zh-CN',\n",
" 'segment': ''}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from datasets import load_dataset\n",
"from datasets import load_dataset, DatasetDict\n",
"\n",
"common_voice = DatasetDict()\n",
"\n",
"common_voice[\"train\"] = load_dataset(dataset_name, language_abbr, split=\"train+validation\", trust_remote_code=True)\n",
"common_voice[\"test\"] = load_dataset(dataset_name, language_abbr, split=\"test\", trust_remote_code=True)\n",
"common_voice[\"train\"][0]"
]
},
{
"cell_type": "markdown",
"id": "3c81faa4-d8fe-4cc7-afe6-4c2615b9050f",
"metadata": {},
"source": [
"## 预处理训练数据集\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5822025f-7f8e-4141-8bfe-d8822d0da20f",
"metadata": {},
"outputs": [],
"source": [
"from transformers import AutoFeatureExtractor, AutoTokenizer, AutoProcessor\n",
"\n",
"feature_extractor = AutoFeatureExtractor.from_pretrained(model_name_or_path)\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(\n",
" model_name_or_path, language=language, task=task)\n",
"\n",
"processor = AutoProcessor.from_pretrained(\n",
" model_name_or_path, language=language, task=task)"
]
},
{
"cell_type": "markdown",
"id": "f394e5cd-23b8-413e-8bde-88c3542b84fa",
"metadata": {},
"source": [
"#### 移除数据集中不必要的字段"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "1690dc5a-c1f7-4556-9be3-d31ad888e52e",
"metadata": {},
"outputs": [],
"source": [
"common_voice = common_voice.remove_columns(\n",
" [\"accent\", \"age\", \"client_id\", \"down_votes\", \"gender\", \"locale\", \"path\", \"segment\", \"up_votes\"]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "309aff16-ea26-4474-af54-7ef244783999",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'audio': {'path': '/store/jxzhang/.cache/huggingface/datasets/downloads/extracted/edf8cf7fef3457433a3a59929c4c4809972172377467a8f189ac185f3d5e4b53/zh-CN_train_0/common_voice_zh-CN_33211332.mp3',\n",
" 'array': array([-6.82121026e-13, -2.27373675e-12, -2.27373675e-12, ...,\n",
" 1.21667399e-05, 3.23003678e-06, -2.43066324e-07]),\n",
" 'sampling_rate': 48000},\n",
" 'sentence': '性喜温暖润湿气候且耐寒。'}"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"common_voice[\"train\"][0]"
]
},
{
"cell_type": "markdown",
"id": "881546ab-72e4-4bcf-852f-a8be736164b7",
"metadata": {},
"source": [
"#### 降采样音频数据\n",
"\n",
"查看`common_voice` 数据集介绍，你会发现其音频是以48kHz的采样率进行采样的.\n",
"\n",
"而`Whisper`模型是在16kHZ的音频输入上预训练的，因此我们需要将音频输入降采样以匹配模型预训练时使用的采样率。\n",
"\n",
"通过在音频列上使用`cast_column`方法，并将`sampling_rate`设置为16kHz来对音频进行降采样。\n",
"\n",
"下次调用时，音频输入将实时重新取样："
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "5fc451cc-e21e-473c-a702-d7d6ed098f91",
"metadata": {},
"outputs": [],
"source": [
"from datasets import Audio\n",
"\n",
"common_voice = common_voice.cast_column(\"audio\", Audio(sampling_rate=16000))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "cc3d7fcc-7c34-41c8-9857-5a6e883f6115",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'audio': {'path': '/store/jxzhang/.cache/huggingface/datasets/downloads/extracted/edf8cf7fef3457433a3a59929c4c4809972172377467a8f189ac185f3d5e4b53/zh-CN_train_0/common_voice_zh-CN_33211332.mp3',\n",
" 'array': array([ 5.09317033e-11, -7.27595761e-12, -6.54836185e-11, ...,\n",
" -5.96661994e-06, 2.71382887e-05, 1.29687978e-05]),\n",
" 'sampling_rate': 16000},\n",
" 'sentence': '性喜温暖润湿气候且耐寒。'}"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"common_voice[\"train\"][0]"
]
},
{
"cell_type": "markdown",
"id": "ee55908f-3ea3-4aee-8062-6f8d3a6573b9",
"metadata": {},
"source": [
"### 整合以上数据处理为一个函数\n",
"\n",
"该数据预处理函数应该包括：\n",
"- 通过加载音频列将音频输入重新采样为16kHZ。\n",
"- 使用特征提取器从音频数组计算输入特征。\n",
"- 将句子列标记化为输入标签。"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "58f42c35-35ba-4d6b-9d15-095963cec67c",
"metadata": {},
"outputs": [],
"source": [
"def prepare_dataset(batch):\n",
" audio = batch[\"audio\"]\n",
" batch[\"input_features\"] = feature_extractor(audio[\"array\"], sampling_rate=audio[\"sampling_rate\"]).input_features[0]\n",
" batch[\"labels\"] = tokenizer(batch[\"sentence\"]).input_ids\n",
" return batch"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "392f7856-a720-40a7-af7e-40e185fc315b",
"metadata": {},
"outputs": [],
"source": [
"common_voice = common_voice.map(\n",
" prepare_dataset, remove_columns=common_voice.column_names[\"train\"]\n",
")"
]
},
{
"cell_type": "markdown",
"id": "84ec184e-d840-40b6-99af-d11392273442",
"metadata": {},
"source": [
"创建一个`DataCollator`类来将每个批次中的`attention_mask`填充到最大长度，并用`-100`替换填充值，以便在损失函数中被忽略。\n",
"\n",
"然后初始化数据收集器的实例："
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "4c89ffcf-c805-48c2-b7d3-ae01b687178c",
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"\n",
"from dataclasses import dataclass\n",
"from typing import Any, Dict, List, Union\n",
"\n",
"\n",
"@dataclass\n",
"class DataCollatorSpeechSeq2SeqWithPadding:\n",
" processor: Any\n",
"\n",
" def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:\n",
" input_features = [{\"input_features\": feature[\"input_features\"]} for feature in features]\n",
" batch = self.processor.feature_extractor.pad(input_features, return_tensors=\"pt\")\n",
"\n",
" label_features = [{\"input_ids\": feature[\"labels\"]} for feature in features]\n",
" labels_batch = self.processor.tokenizer.pad(label_features, return_tensors=\"pt\")\n",
"\n",
" labels = labels_batch[\"input_ids\"].masked_fill(labels_batch.attention_mask.ne(1), -100)\n",
"\n",
" if (labels[:, 0] == self.processor.tokenizer.bos_token_id).all().cpu().item():\n",
" labels = labels[:, 1:]\n",
"\n",
" batch[\"labels\"] = labels\n",
"\n",
" return batch\n",
"\n",
"\n",
"data_collator = DataCollatorSpeechSeq2SeqWithPadding(processor=processor)"
]
},
{
"cell_type": "markdown",
"id": "80ecd4bc-01fd-4286-afe5-fe2639ae15a1",
"metadata": {},
"source": [
"## 训练模型"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "f9fcb121-fa5c-4c30-8bdc-9ab08ab75427",
"metadata": {},
"outputs": [],
"source": [
"from transformers import AutoModelForSpeechSeq2Seq\n",
"\n",
"model = AutoModelForSpeechSeq2Seq.from_pretrained(model_name_or_path, load_in_8bit=True, device_map=\"auto\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "2cb016f1-e6e9-4fd8-9c8b-72fd23be92d3",
"metadata": {},
"outputs": [],
"source": [
"model.config.forced_decoder_ids = None\n",
"model.config.suppress_tokens = []"
]
},
{
"cell_type": "markdown",
"id": "25ba1fa0-ea15-48d9-8c16-70df9f0b60b1",
"metadata": {},
"source": [
"为了准备模型进行int8量化，使用 `prepare_model_for_int8_training` 函数来处理模型：\n",
"- 将所有非int8模块转换为完全精度（fp32）以保持稳定性\n",
"- 在输入嵌入层上添加前向钩子，计算输入隐藏状态的梯度\n",
"- 启用渐变检查点以进行更高效的内存训练"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "1ee34359-fe1b-48f1-827c-6a8ec4a53af7",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/peft/utils/other.py:141: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.\n",
" warnings.warn(\n"
]
}
],
"source": [
"from peft import prepare_model_for_int8_training\n",
"\n",
"model = prepare_model_for_int8_training(model)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "24b6f8a2-867f-4ed5-bad5-15ca9fd9547c",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 15,
"id": "cdf6bc9c-6d2c-4dbf-b09e-a89cb1041c46",
"metadata": {},
"outputs": [],
"source": [
"from peft import LoraConfig, PeftModel, LoraModel, LoraConfig, get_peft_model\n",
"\n",
"config = LoraConfig(\n",
" r=8,\n",
" lora_alpha=64,\n",
" target_modules=[\"q_proj\", \"v_proj\"],\n",
" lora_dropout=0.05,\n",
" bias=\"none\")"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "b74c7508-e6f4-42d8-8aaf-fe83c5977c35",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"trainable params: 3,932,160 || all params: 1,547,237,120 || trainable%: 0.25414074863974306\n"
]
}
],
"source": [
"model = get_peft_model(model, config)\n",
"model.print_trainable_parameters()"
]
},
{
"cell_type": "markdown",
"id": "1cc6b26a-3e54-4a46-9b36-a048b40a37d7",
"metadata": {},
"source": [
"### 演示需要，只训练了100 steps。建议同学改为默认的 3个 epochs 完整训练一个中文语音识别模型。"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "11f259c8-dbcf-4a7f-bbb5-821ab104efee",
"metadata": {},
"outputs": [],
"source": [
"from transformers import Seq2SeqTrainingArguments\n",
"\n",
"# 设置序列到序列模型训练的参数\n",
"training_args = Seq2SeqTrainingArguments(\n",
" output_dir=\"models/whisper-large-v2-asr-int8\", # 指定模型输出和保存的目录\n",
" per_device_train_batch_size=batch_size, # 每个设备上的训练批量大小\n",
" gradient_accumulation_steps=1, # 梯度累积步数，在每次优化器步骤之前累积的更新步数\n",
" learning_rate=1e-3, # 学习率\n",
" warmup_steps=50, # 在训练初期增加学习率的步数，有助于稳定训练\n",
" # max_steps=100, # 训练总步数\n",
" num_train_epochs=3, # 训练的总轮数\n",
" evaluation_strategy=\"epoch\", # 设置评估策略，这里是在每个epoch结束时进行评估\n",
" fp16=True, # 启用混合精度训练，可以提高训练速度，同时减少内存使用\n",
" per_device_eval_batch_size=batch_size, # 每个设备上的评估批量大小\n",
" generation_max_length=128, # 生成任务的最大长度\n",
" logging_steps=25, # 指定日志记录的步骤，用于跟踪训练进度\n",
" remove_unused_columns=False, # 是否删除不使用的列，以减少数据处理开销\n",
" label_names=[\"labels\"], # 指定标签列的名称，用于训练过程中\n",
")"
]
},
{
"cell_type": "markdown",
"id": "c57ee183-b16f-4313-97f6-0df6c0f5f467",
"metadata": {},
"source": [
"#### 训练过程保存状态的回调，长时期训练建议使用"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "2ce443d9-f309-4c03-bd74-c6842292b713",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR\n",
"from transformers import Seq2SeqTrainer, TrainerCallback, Seq2SeqTrainingArguments, TrainerState, TrainerControl\n",
"\n",
"class SavePeftModelCallback(TrainerCallback):\n",
" def on_save(\n",
" self,\n",
" args: Seq2SeqTrainingArguments,\n",
" state: TrainerState,\n",
" control: TrainerControl,\n",
" **kwargs,\n",
" ):\n",
" checkpoint_folder = os.path.join(args.output_dir, f\"{PREFIX_CHECKPOINT_DIR}-{state.global_step}\")\n",
"\n",
" peft_model_path = os.path.join(checkpoint_folder, \"adapter_model\")\n",
" kwargs[\"model\"].save_pretrained(peft_model_path)\n",
"\n",
" pytorch_model_path = os.path.join(checkpoint_folder, \"pytorch_model.bin\")\n",
" if os.path.exists(pytorch_model_path):\n",
" os.remove(pytorch_model_path)\n",
" return control"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "f8a52ed7-cae0-4aba-818e-87717430d908",
"metadata": {},
"outputs": [],
"source": [
"trainer = Seq2SeqTrainer(\n",
" args=training_args,\n",
" model=model,\n",
" train_dataset=common_voice[\"train\"],\n",
" eval_dataset=common_voice[\"test\"],\n",
" data_collator=data_collator,\n",
" tokenizer=processor.feature_extractor,\n",
" callbacks=[SavePeftModelCallback],\n",
")\n",
"model.config.use_cache = False"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "6973bed7-8f53-4d55-966c-f037941e5ef3",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.\n",
" warnings.warn(\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/torch/utils/checkpoint.py:61: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n",
" warnings.warn(\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/bitsandbytes/autograd/_functions.py:322: UserWarning: MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization\n",
" warnings.warn(f\"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization\")\n"
]
},
{
"data": {
"text/html": [
"\n",
" <div>\n",
" \n",
" <progress value='1860' max='1860' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
" [1860/1860 7:48:09, Epoch 3/3]\n",
" </div>\n",
" <table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: left;\">\n",
" <th>Epoch</th>\n",
" <th>Training Loss</th>\n",
" <th>Validation Loss</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>0.341900</td>\n",
" <td>0.264468</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>0.259600</td>\n",
" <td>0.248249</td>\n",
" </tr>\n",
" <tr>\n",
" <td>3</td>\n",
" <td>0.214400</td>\n",
" <td>0.248773</td>\n",
" </tr>\n",
" </tbody>\n",
"</table><p>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.\n",
" warnings.warn(\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/torch/utils/checkpoint.py:61: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n",
" warnings.warn(\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/bitsandbytes/autograd/_functions.py:322: UserWarning: MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization\n",
" warnings.warn(f\"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization\")\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.\n",
" warnings.warn(\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/torch/utils/checkpoint.py:61: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n",
" warnings.warn(\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/bitsandbytes/autograd/_functions.py:322: UserWarning: MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization\n",
" warnings.warn(f\"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization\")\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.\n",
" warnings.warn(\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/torch/utils/checkpoint.py:61: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n",
" warnings.warn(\n",
"/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/bitsandbytes/autograd/_functions.py:322: UserWarning: MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization\n",
" warnings.warn(f\"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization\")\n"
]
},
{
"data": {
"text/plain": [
"TrainOutput(global_step=1860, training_loss=0.32258521408163093, metrics={'train_runtime': 28110.1202, 'train_samples_per_second': 4.23, 'train_steps_per_second': 0.066, 'total_flos': 2.531417002463232e+20, 'train_loss': 0.32258521408163093, 'epoch': 3.0})"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"trainer.train()"
]
},
{
"cell_type": "markdown",
"id": "620992c3-64f5-48f9-8e66-fdc5f6a27427",
"metadata": {},
"source": [
"### 保存 LoRA 模型"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "53310565-7313-46a7-acf1-215970fd4f8e",
"metadata": {},
"outputs": [],
"source": [
"model.save_pretrained(\"models/whisper-large-v2-asr-int8\")"
]
},
{
"cell_type": "markdown",
"id": "dcfe9611-eee5-462f-8cb8-fed86eec76e0",
"metadata": {},
"source": [
"### 使用 Pipiline 加载 LoRA 模型，实现自动语音识别任务"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "426d7520-62cb-42bb-a4dd-000aa607b105",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"5.763907432556152"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from transformers import AutoModelForSpeechSeq2Seq\n",
"\n",
"my_model_name_or_path = \"yqzhangjx/whisper-large-v2-asr-int8\"\n",
"\n",
"model = AutoModelForSpeechSeq2Seq.from_pretrained(my_model_name_or_path, device_map=\"auto\")\n",
"\n",
"model.get_memory_footprint()/1024**3"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "7536c488-0526-4c12-baaf-b4f7c7075be6",
"metadata": {},
"outputs": [],
"source": [
"from transformers import AutoFeatureExtractor, AutoTokenizer, AutoProcessor\n",
"\n",
"feature_extractor = AutoFeatureExtractor.from_pretrained(model_name_or_path)\n",
"tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, language=language, task=task)\n",
"processor = AutoProcessor.from_pretrained(model_name_or_path, language=language, task=task)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "18181692-a143-44ee-b56c-e754d308e0ec",
"metadata": {},
"outputs": [],
"source": [
"test_audio = \"data/audio/test_zh.flac\""
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9d494647-082c-4e48-9486-7945618ae679",
"metadata": {},
"outputs": [],
"source": [
"from transformers import AutomaticSpeechRecognitionPipeline\n",
"\n",
"pipeline = AutomaticSpeechRecognitionPipeline(model=model, tokenizer=tokenizer, feature_extractor=feature_extractor)\n",
"\n",
"forced_decoder_ids = processor.get_decoder_prompt_ids(language=\"chinese\", task=task)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "c3eac486-169f-41ad-b9c3-69f2c27c3e1f",
"metadata": {},
"outputs": [],
"source": [
"with torch.cuda.amp.autocast():\n",
" text = pipeline(test_audio, generate_kwargs={\"forced_decoder_ids\": forced_decoder_ids}, max_new_tokens=255)[\"text\"]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "cc4b24b2-c65b-4e63-8f16-26c72039a38d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'这是一段测试用于Whisper Large V2模型的自动语音识别测试。'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"text"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "89f49787-6ab4-4bc1-91b8-a1c104c9feaf",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "0285dd19-229e-4241-b680-71e25ab51dde",
"metadata": {},
"source": [
"#### Homework 1: 为中文语料的训练过程增加过程评估，观察 Train Loss 和 Validation Loss 变化；\n",
"#### Homework 2: LoRA 模型训练完成后，使用测试集进行完整的模型评估"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0c90ad4c-70eb-43d1-96ec-cc74c4bae345",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "b24fccce-fec3-48a3-b43c-b9077788521d",
"metadata": {},
"source": [
"## 评估模型"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "b021c6a8-645d-44f7-970b-f410180787a6",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "5874cd7f7cba4c1d9d89092923e0b8a5",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading builder script: 0%| | 0.00/4.49k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import evaluate\n",
"\n",
"# 词错误率（WER）是评估ASR模型常用的指标。从 Evaluate加载 WER 指标\n",
"metric = evaluate.load(\"wer\")"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "5156ce16-0e04-4e41-b308-52c6c9b2a20d",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"PeftModel(\n",
" (base_model): LoraModel(\n",
" (model): WhisperForConditionalGeneration(\n",
" (model): WhisperModel(\n",
" (encoder): WhisperEncoder(\n",
" (conv1): Conv1d(80, 1280, kernel_size=(3,), stride=(1,), padding=(1,))\n",
" (conv2): Conv1d(1280, 1280, kernel_size=(3,), stride=(2,), padding=(1,))\n",
" (embed_positions): Embedding(1500, 1280)\n",
" (layers): ModuleList(\n",
" (0-31): 32 x WhisperEncoderLayer(\n",
" (self_attn): WhisperSdpaAttention(\n",
" (k_proj): Linear8bitLt(in_features=1280, out_features=1280, bias=False)\n",
" (v_proj): lora.Linear8bitLt(\n",
" (base_layer): Linear8bitLt(in_features=1280, out_features=1280, bias=True)\n",
" (lora_dropout): ModuleDict(\n",
" (default): Dropout(p=0.05, inplace=False)\n",
" )\n",
" (lora_A): ModuleDict(\n",
" (default): Linear(in_features=1280, out_features=8, bias=False)\n",
" )\n",
" (lora_B): ModuleDict(\n",
" (default): Linear(in_features=8, out_features=1280, bias=False)\n",
" )\n",
" (lora_embedding_A): ParameterDict()\n",
" (lora_embedding_B): ParameterDict()\n",
" )\n",
" (q_proj): lora.Linear8bitLt(\n",
" (base_layer): Linear8bitLt(in_features=1280, out_features=1280, bias=True)\n",
" (lora_dropout): ModuleDict(\n",
" (default): Dropout(p=0.05, inplace=False)\n",
" )\n",
" (lora_A): ModuleDict(\n",
" (default): Linear(in_features=1280, out_features=8, bias=False)\n",
" )\n",
" (lora_B): ModuleDict(\n",
" (default): Linear(in_features=8, out_features=1280, bias=False)\n",
" )\n",
" (lora_embedding_A): ParameterDict()\n",
" (lora_embedding_B): ParameterDict()\n",
" )\n",
" (out_proj): Linear8bitLt(in_features=1280, out_features=1280, bias=True)\n",
" )\n",
" (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)\n",
" (activation_fn): GELUActivation()\n",
" (fc1): Linear8bitLt(in_features=1280, out_features=5120, bias=True)\n",
" (fc2): Linear8bitLt(in_features=5120, out_features=1280, bias=True)\n",
" (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)\n",
" )\n",
" )\n",
" (layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)\n",
" )\n",
" (decoder): WhisperDecoder(\n",
" (embed_tokens): Embedding(51865, 1280, padding_idx=50257)\n",
" (embed_positions): WhisperPositionalEmbedding(448, 1280)\n",
" (layers): ModuleList(\n",
" (0-31): 32 x WhisperDecoderLayer(\n",
" (self_attn): WhisperSdpaAttention(\n",
" (k_proj): Linear8bitLt(in_features=1280, out_features=1280, bias=False)\n",
" (v_proj): lora.Linear8bitLt(\n",
" (base_layer): Linear8bitLt(in_features=1280, out_features=1280, bias=True)\n",
" (lora_dropout): ModuleDict(\n",
" (default): Dropout(p=0.05, inplace=False)\n",
" )\n",
" (lora_A): ModuleDict(\n",
" (default): Linear(in_features=1280, out_features=8, bias=False)\n",
" )\n",
" (lora_B): ModuleDict(\n",
" (default): Linear(in_features=8, out_features=1280, bias=False)\n",
" )\n",
" (lora_embedding_A): ParameterDict()\n",
" (lora_embedding_B): ParameterDict()\n",
" )\n",
" (q_proj): lora.Linear8bitLt(\n",
" (base_layer): Linear8bitLt(in_features=1280, out_features=1280, bias=True)\n",
" (lora_dropout): ModuleDict(\n",
" (default): Dropout(p=0.05, inplace=False)\n",
" )\n",
" (lora_A): ModuleDict(\n",
" (default): Linear(in_features=1280, out_features=8, bias=False)\n",
" )\n",
" (lora_B): ModuleDict(\n",
" (default): Linear(in_features=8, out_features=1280, bias=False)\n",
" )\n",
" (lora_embedding_A): ParameterDict()\n",
" (lora_embedding_B): ParameterDict()\n",
" )\n",
" (out_proj): Linear8bitLt(in_features=1280, out_features=1280, bias=True)\n",
" )\n",
" (activation_fn): GELUActivation()\n",
" (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)\n",
" (encoder_attn): WhisperSdpaAttention(\n",
" (k_proj): Linear8bitLt(in_features=1280, out_features=1280, bias=False)\n",
" (v_proj): lora.Linear8bitLt(\n",
" (base_layer): Linear8bitLt(in_features=1280, out_features=1280, bias=True)\n",
" (lora_dropout): ModuleDict(\n",
" (default): Dropout(p=0.05, inplace=False)\n",
" )\n",
" (lora_A): ModuleDict(\n",
" (default): Linear(in_features=1280, out_features=8, bias=False)\n",
" )\n",
" (lora_B): ModuleDict(\n",
" (default): Linear(in_features=8, out_features=1280, bias=False)\n",
" )\n",
" (lora_embedding_A): ParameterDict()\n",
" (lora_embedding_B): ParameterDict()\n",
" )\n",
" (q_proj): lora.Linear8bitLt(\n",
" (base_layer): Linear8bitLt(in_features=1280, out_features=1280, bias=True)\n",
" (lora_dropout): ModuleDict(\n",
" (default): Dropout(p=0.05, inplace=False)\n",
" )\n",
" (lora_A): ModuleDict(\n",
" (default): Linear(in_features=1280, out_features=8, bias=False)\n",
" )\n",
" (lora_B): ModuleDict(\n",
" (default): Linear(in_features=8, out_features=1280, bias=False)\n",
" )\n",
" (lora_embedding_A): ParameterDict()\n",
" (lora_embedding_B): ParameterDict()\n",
" )\n",
" (out_proj): Linear8bitLt(in_features=1280, out_features=1280, bias=True)\n",
" )\n",
" (encoder_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)\n",
" (fc1): Linear8bitLt(in_features=1280, out_features=5120, bias=True)\n",
" (fc2): Linear8bitLt(in_features=5120, out_features=1280, bias=True)\n",
" (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)\n",
" )\n",
" )\n",
" (layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)\n",
" )\n",
" )\n",
" (proj_out): Linear(in_features=1280, out_features=51865, bias=False)\n",
" )\n",
" )\n",
")"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from torch.utils.data import DataLoader\n",
"from tqdm import tqdm\n",
"import numpy as np\n",
"import gc\n",
"\n",
"eval_dataloader = DataLoader(common_voice[\"test\"], batch_size=8, collate_fn=data_collator)\n",
"\n",
"model.eval()"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "9120279e-b10a-44ea-9275-2152ec204fae",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/1323 [00:00<?, ?it/s]/data/miniconda3/envs/jxzhang/lib/python3.11/site-packages/bitsandbytes/autograd/_functions.py:322: UserWarning: MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization\n",
" warnings.warn(f\"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization\")\n",
"100%|██████████| 1323/1323 [3:13:07<00:00, 8.76s/it] \n"
]
}
],
"source": [
"for step, batch in enumerate(tqdm(eval_dataloader)):\n",
" with torch.cuda.amp.autocast():\n",
" with torch.no_grad():\n",
" generated_tokens = (\n",
" model.generate(\n",
" input_features=batch[\"input_features\"].to(\"cuda\"),\n",
" decoder_input_ids=batch[\"labels\"][:, :4].to(\"cuda\"),\n",
" max_new_tokens=255,\n",
" )\n",
" .cpu()\n",
" .numpy()\n",
" )\n",
" labels = batch[\"labels\"].cpu().numpy()\n",
" labels = np.where(labels != -100, labels, tokenizer.pad_token_id)\n",
" decoded_preds = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)\n",
" decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)\n",
" metric.add_batch(\n",
" predictions=decoded_preds,\n",
" references=decoded_labels,\n",
" )\n",
" del generated_tokens, labels, batch\n",
" gc.collect()"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "aad4d7e8-ee0d-484a-9ae7-490c8b9898a0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"wer=54.73445473445473\n"
]
}
],
"source": [
"wer = 100 * metric.compute()\n",
"print(f\"{wer=}\")"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "4120d924-c684-44af-8a1d-76aaf506bd08",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "65c2e25ce2434db2a59617adf7439064",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"adapter_model.safetensors: 0%| | 0.00/15.8M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"CommitInfo(commit_url='https://huggingface.co/yqzhangjx/whisper-large-v2-finetune-for-common_voice_11_0/commit/e9a78de42addc1cfb814188de95de3e97f9281c6', commit_message='Upload model', commit_description='', oid='e9a78de42addc1cfb814188de95de3e97f9281c6', pr_url=None, pr_revision=None, pr_num=None)"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.push_to_hub('whisper-large-v2-asr-int8')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b740c690-35ff-4375-b59f-3c6de5155ec0",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"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": "3.9.18"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|