Spaces:
Sleeping
Sleeping
File size: 56,771 Bytes
69c0ff1 c2fa877 69c0ff1 c2fa877 69c0ff1 c2fa877 69c0ff1 c2fa877 69c0ff1 c2fa877 69c0ff1 c2fa877 69c0ff1 c2fa877 69c0ff1 1e32511 69c0ff1 c2fa877 1e32511 c2fa877 69c0ff1 c2fa877 69c0ff1 c2fa877 69c0ff1 1e32511 69c0ff1 c2fa877 69c0ff1 1e32511 69c0ff1 1e32511 c2fa877 1e32511 c2fa877 1e32511 c2fa877 1e32511 c2fa877 69c0ff1 1e32511 69c0ff1 1e32511 69c0ff1 1e32511 69c0ff1 c2fa877 69c0ff1 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"import dotenv\n",
"import pandas as pd\n",
"from httpx import Timeout\n",
"from pydantic import BaseModel\n",
"from langchain_core.prompts import (\n",
" ChatPromptTemplate,\n",
" SystemMessagePromptTemplate,\n",
" HumanMessagePromptTemplate,\n",
")\n",
"from langchain_openai import ChatOpenAI\n",
"from langchain_community.callbacks import get_openai_callback\n",
"\n",
"import data.samples_to_split as samples\n",
"\n",
"from src.lc_callbacks import LCMessageLoggerAsync\n",
"from src.utils import GPTModels\n",
"from src.text_split_chain import create_split_text_chain"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dotenv.load_dotenv()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## voices eda"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(468, 14)\n"
]
}
],
"source": [
"# df = pd.read_csv('data/11labs_tts_voices.csv')\n",
"df = pd.read_csv('data/11labs_available_tts_voices.csv')\n",
"df[\"age\"] = df[\"age\"].str.replace(\" \", \"_\").str.replace(\"-\", \"_\")\n",
"print(df.shape)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['voice_id', 'name', 'preview_url', 'owner_id', 'permission_on_resource',\n",
" 'is_legacy', 'is_mixed', 'accent', 'description', 'age', 'gender',\n",
" 'category', 'language', 'descriptive'],\n",
" dtype='object')"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"language\n",
"NaN 264\n",
"en 203\n",
"romanian 1\n",
"Name: count, dtype: int64"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['language'].value_counts(dropna=False)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"gender\n",
"female 231\n",
"male 230\n",
"neutral 6\n",
"non-binary 1\n",
"Name: count, dtype: int64"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['gender'].value_counts(dropna=False)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"age\n",
"middle_aged 183\n",
"young 143\n",
"old 140\n",
"NaN 2\n",
"Name: count, dtype: int64"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['age'].value_counts(dropna=False)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>gender</th>\n",
" <th>female</th>\n",
" <th>male</th>\n",
" <th>neutral</th>\n",
" <th>non-binary</th>\n",
" </tr>\n",
" <tr>\n",
" <th>age</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>middle_aged</th>\n",
" <td>48</td>\n",
" <td>130</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>old</th>\n",
" <td>100</td>\n",
" <td>39</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>young</th>\n",
" <td>83</td>\n",
" <td>59</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NaN</th>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"gender female male neutral non-binary\n",
"age \n",
"middle_aged 48 130 4 1\n",
"old 100 39 1 0\n",
"young 83 59 1 0\n",
"NaN 0 2 0 0"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.groupby(['age', 'gender'], dropna=False)['voice_id'].count().unstack(fill_value=0)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>gender</th>\n",
" <th>female</th>\n",
" <th>male</th>\n",
" <th>neutral</th>\n",
" <th>non-binary</th>\n",
" </tr>\n",
" <tr>\n",
" <th>language</th>\n",
" <th>age</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">en</th>\n",
" <th>middle_aged</th>\n",
" <td>30</td>\n",
" <td>91</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>old</th>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>young</th>\n",
" <td>34</td>\n",
" <td>38</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NaN</th>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>romanian</th>\n",
" <th>old</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"3\" valign=\"top\">NaN</th>\n",
" <th>middle_aged</th>\n",
" <td>18</td>\n",
" <td>39</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>old</th>\n",
" <td>96</td>\n",
" <td>36</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>young</th>\n",
" <td>49</td>\n",
" <td>21</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"gender female male neutral non-binary\n",
"language age \n",
"en middle_aged 30 91 2 0\n",
" old 3 3 0 0\n",
" young 34 38 0 0\n",
" NaN 0 2 0 0\n",
"romanian old 1 0 0 0\n",
"NaN middle_aged 18 39 2 1\n",
" old 96 36 1 0\n",
" young 49 21 1 0"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.groupby(['language', 'age', 'gender'], dropna=False)['voice_id'].count().unstack(fill_value=0)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"descriptive\n",
"confident 64\n",
"calm 44\n",
"casual 34\n",
"pleasant 31\n",
"deep 28\n",
"NaN 26\n",
"professional 26\n",
"upbeat 22\n",
"wise 20\n",
"formal 17\n",
"intense 13\n",
"serious 13\n",
"meditative 11\n",
"modulated 11\n",
"excited 10\n",
"husky 10\n",
"mature 8\n",
"classy 8\n",
"chill 7\n",
"neutral 7\n",
"crisp 6\n",
"gentle 6\n",
"childish 6\n",
"hyped 6\n",
"cute 5\n",
"sassy 4\n",
"soft 4\n",
"rough 3\n",
"grumpy 3\n",
"whispery 3\n",
"robotic 3\n",
"relaxed 3\n",
"raspy 2\n",
"cheeky 1\n",
"sad 1\n",
"anxious 1\n",
"motivational 1\n",
"Name: count, dtype: int64"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['descriptive'].value_counts(dropna=False)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(39, 14)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"age_group = 'old'\n",
"gender = 'male'\n",
"df_filtered = df[(df['age'] == age_group) & (df['gender'] == gender)]\n",
"df_filtered.shape"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>voice_id</th>\n",
" <th>name</th>\n",
" <th>preview_url</th>\n",
" <th>owner_id</th>\n",
" <th>permission_on_resource</th>\n",
" <th>is_legacy</th>\n",
" <th>is_mixed</th>\n",
" <th>accent</th>\n",
" <th>description</th>\n",
" <th>age</th>\n",
" <th>gender</th>\n",
" <th>category</th>\n",
" <th>language</th>\n",
" <th>descriptive</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>245</th>\n",
" <td>ugI9yHu7QMtMOjozITa3</td>\n",
" <td>Nimbus - deep & meditative</td>\n",
" <td>https://storage.googleapis.com/eleven-public-p...</td>\n",
" <td>NaN</td>\n",
" <td>admin</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>american</td>\n",
" <td>NaN</td>\n",
" <td>old</td>\n",
" <td>male</td>\n",
" <td>entertainment_tv</td>\n",
" <td>NaN</td>\n",
" <td>neutral</td>\n",
" </tr>\n",
" <tr>\n",
" <th>284</th>\n",
" <td>1SJjcjy45jFu6erSHVWq</td>\n",
" <td>Howard - American Radio Voice</td>\n",
" <td>https://storage.googleapis.com/eleven-public-p...</td>\n",
" <td>NaN</td>\n",
" <td>admin</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>american</td>\n",
" <td>NaN</td>\n",
" <td>old</td>\n",
" <td>male</td>\n",
" <td>advertisement</td>\n",
" <td>NaN</td>\n",
" <td>modulated</td>\n",
" </tr>\n",
" <tr>\n",
" <th>362</th>\n",
" <td>oUAzGw71wG6JCbHMK33s</td>\n",
" <td>Mark - calm and wise teacher</td>\n",
" <td>https://storage.googleapis.com/eleven-public-p...</td>\n",
" <td>NaN</td>\n",
" <td>admin</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>british</td>\n",
" <td>NaN</td>\n",
" <td>old</td>\n",
" <td>male</td>\n",
" <td>informative_educational</td>\n",
" <td>NaN</td>\n",
" <td>deep</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" voice_id name \\\n",
"245 ugI9yHu7QMtMOjozITa3 Nimbus - deep & meditative \n",
"284 1SJjcjy45jFu6erSHVWq Howard - American Radio Voice \n",
"362 oUAzGw71wG6JCbHMK33s Mark - calm and wise teacher \n",
"\n",
" preview_url owner_id \\\n",
"245 https://storage.googleapis.com/eleven-public-p... NaN \n",
"284 https://storage.googleapis.com/eleven-public-p... NaN \n",
"362 https://storage.googleapis.com/eleven-public-p... NaN \n",
"\n",
" permission_on_resource is_legacy is_mixed accent description age \\\n",
"245 admin False False american NaN old \n",
"284 admin False False american NaN old \n",
"362 admin False False british NaN old \n",
"\n",
" gender category language descriptive \n",
"245 male entertainment_tv NaN neutral \n",
"284 male advertisement NaN modulated \n",
"362 male informative_educational NaN deep "
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_filtered.sample(3)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['HrciSEXYMv69BAJ4ixOW', 'oUAzGw71wG6JCbHMK33s', 'Zl8mecngHM53e1hl151S']"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_filtered.sample(3)['voice_id'].to_list()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## split text into character phrases"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-10-10 02:34:52,755 [INFO] audio-books (lc_callbacks.py): call to <failed to determine LLM> with 2 messages:\n",
"{'role': 'system', 'content': 'you are provided with the book sample.\\nplease rewrite it and insert xml tags indicating character to whom current phrase belongs.\\nfor example: <narrator>I looked at her</narrator><Jill>What are you looking at?</Jill>\\n\\nNotes:\\n- sometimes narrator is one of characters taking part in the action.\\nin this case use narrator\\'s name (if available) instead of \"narrator\"\\n- if it\\'s impossible to identify character name from the text provided, use codes \"c1\", \"c2\", etc,\\nwhere \"c\" prefix means character and number is used to enumerate unknown characters\\n- all quotes of direct speech must be attributed to characters, for example:\\n<Tom>“She’s a nice girl,”</Tom><narrator>said Tom after a moment.</narrator>\\nmind that sometimes narrator could also be a character.\\n- use ALL available context to determine the character.\\nsometimes the character name becomes clear from the following phrases\\n- DO NOT include in your response anything except for the original text with character xml tags!!!\\n'}\n",
"{'role': 'human', 'content': 'Here is the book sample:\\n---\\nInside, the crimson room bloomed with light. Tom and Miss Baker sat at\\neither end of the long couch and she read aloud to him from the\\nSaturday Evening Post—the words, murmurous and uninflected, running\\ntogether in a soothing tune. The lamplight, bright on his boots and\\ndull on the autumn-leaf yellow of her hair, glinted along the paper as\\nshe turned a page with a flutter of slender muscles in her arms.\\n\\nWhen we came in she held us silent for a moment with a lifted hand.\\n\\n“To be continued,” she said, tossing the magazine on the table, “in\\nour very next issue.”\\n\\nHer body asserted itself with a restless movement of her knee, and she\\nstood up.\\n\\n“Ten o’clock,” she remarked, apparently finding the time on the\\nceiling. “Time for this good girl to go to bed.”\\n\\n“Jordan’s going to play in the tournament tomorrow,” explained Daisy,\\n“over at Westchester.”\\n\\n“Oh—you’re Jordan Baker.”\\n\\nI knew now why her face was familiar—its pleasing contemptuous\\nexpression had looked out at me from many rotogravure pictures of the\\nsporting life at Asheville and Hot Springs and Palm Beach. I had heard\\nsome story of her too, a critical, unpleasant story, but what it was I\\nhad forgotten long ago.\\n\\n“Good night,” she said softly. “Wake me at eight, won’t you.”\\n\\n“If you’ll get up.”\\n\\n“I will. Good night, Mr. Carraway. See you anon.”\\n\\n“Of course you will,” confirmed Daisy. “In fact I think I’ll arrange a\\nmarriage. Come over often, Nick, and I’ll sort of—oh—fling you\\ntogether. You know—lock you up accidentally in linen closets and push\\nyou out to sea in a boat, and all that sort of thing—”\\n\\n“Good night,” called Miss Baker from the stairs. “I haven’t heard a\\nword.”\\n\\n“She’s a nice girl,” said Tom after a moment. “They oughtn’t to let\\nher run around the country this way.”\\n\\n“Who oughtn’t to?” inquired Daisy coldly.\\n\\n“Her family.”\\n\\n“Her family is one aunt about a thousand years old. Besides, Nick’s\\ngoing to look after her, aren’t you, Nick? She’s going to spend lots\\nof weekends out here this summer. I think the home influence will be\\nvery good for her.”\\n\\nDaisy and Tom looked at each other for a moment in silence.\\n\\n“Is she from New York?” I asked quickly.\\n\\n“From Louisville. Our white girlhood was passed together there. Our\\nbeautiful white—”\\n\\n“Did you give Nick a little heart to heart talk on the veranda?”\\ndemanded Tom suddenly.\\n\\n“Did I?” She looked at me. “I can’t seem to remember, but I think we\\ntalked about the Nordic race. Yes, I’m sure we did. It sort of crept\\nup on us and first thing you know—”\\n\\n“Don’t believe everything you hear, Nick,” he advised me.\\n'}\n",
"2024-10-10 02:35:04,369 [INFO] httpx (_client.py): HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n",
"2024-10-10 02:35:04,383 [INFO] audio-books (lc_callbacks.py): raw LLM response: \"<narrator>Inside, the crimson room bloomed with light. Tom and Miss Baker sat at either end of the long couch and she read aloud to him from the Saturday Evening Post—the words, murmurous and uninflected, running together in a soothing tune. The lamplight, bright on his boots and dull on the autumn-leaf yellow of her hair, glinted along the paper as she turned a page with a flutter of slender muscles in her arms.</narrator>\n",
"\n",
"<narrator>When we came in she held us silent for a moment with a lifted hand.</narrator>\n",
"\n",
"<Jordan>“To be continued,”</Jordan> <narrator>she said, tossing the magazine on the table,</narrator> <Jordan>“in our very next issue.”</Jordan>\n",
"\n",
"<narrator>Her body asserted itself with a restless movement of her knee, and she stood up.</narrator>\n",
"\n",
"<Jordan>“Ten o’clock,”</Jordan> <narrator>she remarked, apparently finding the time on the ceiling.</narrator> <Jordan>“Time for this good girl to go to bed.”</Jordan>\n",
"\n",
"<Daisy>“Jordan’s going to play in the tournament tomorrow,”</Daisy> <narrator>explained Daisy,</narrator> <Daisy>“over at Westchester.”</Daisy>\n",
"\n",
"<narrator>“Oh—you’re Jordan Baker.”</narrator>\n",
"\n",
"<narrator>I knew now why her face was familiar—its pleasing contemptuous expression had looked out at me from many rotogravure pictures of the sporting life at Asheville and Hot Springs and Palm Beach. I had heard some story of her too, a critical, unpleasant story, but what it was I had forgotten long ago.</narrator>\n",
"\n",
"<Jordan>“Good night,”</Jordan> <narrator>she said softly.</narrator> <Jordan>“Wake me at eight, won’t you.”</Jordan>\n",
"\n",
"<Daisy>“If you’ll get up.”</Daisy>\n",
"\n",
"<Jordan>“I will. Good night, Mr. Carraway. See you anon.”</Jordan>\n",
"\n",
"<Daisy>“Of course you will,”</Daisy> <narrator>confirmed Daisy.</narrator> <Daisy>“In fact I think I’ll arrange a marriage. Come over often, Nick, and I’ll sort of—oh—fling you together. You know—lock you up accidentally in linen closets and push you out to sea in a boat, and all that sort of thing—”</Daisy>\n",
"\n",
"<Jordan>“Good night,”</Jordan> <narrator>called Miss Baker from the stairs.</narrator> <Jordan>“I haven’t heard a word.”</Jordan>\n",
"\n",
"<Tom>“She’s a nice girl,”</Tom> <narrator>said Tom after a moment.</narrator> <Tom>“They oughtn’t to let her run around the country this way.”</Tom>\n",
"\n",
"<Daisy>“Who oughtn’t to?”</Daisy> <narrator>inquired Daisy coldly.</narrator>\n",
"\n",
"<Tom>“Her family.”</Tom>\n",
"\n",
"<Daisy>“Her family is one aunt about a thousand years old. Besides, Nick’s going to look after her, aren’t you, Nick? She’s going to spend lots of weekends out here this summer. I think the home influence will be very good for her.”</Daisy>\n",
"\n",
"<narrator>Daisy and Tom looked at each other for a moment in silence.</narrator>\n",
"\n",
"<narrator>“Is she from New York?”</narrator> <narrator>I asked quickly.</narrator>\n",
"\n",
"<Daisy>“From Louisville. Our white girlhood was passed together there. Our beautiful white—”</Daisy>\n",
"\n",
"<Tom>“Did you give Nick a little heart to heart talk on the veranda?”</Tom> <narrator>demanded Tom suddenly.</narrator>\n",
"\n",
"<Daisy>“Did I?”</Daisy> <narrator>She looked at me.</narrator> <Daisy>“I can’t seem to remember, but I think we talked about the Nordic race. Yes, I’m sure we did. It sort of crept up on us and first thing you know—”</Daisy>\n",
"\n",
"<Tom>“Don’t believe everything you hear, Nick,”</Tom> <narrator>he advised me.</narrator>\"\n"
]
}
],
"source": [
"chain = create_split_text_chain(llm_model=GPTModels.GPT_4o)\n",
"# chain = create_split_text_chain(llm_model=GPTModels.GPT_4_TURBO_2024_04_09)\n",
"with get_openai_callback() as cb:\n",
" res = chain.invoke(\n",
" {\"text\": samples.GATSBY_2}, config={\"callbacks\": [LCMessageLoggerAsync()]}\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"SplitTextOutput(text_raw='Inside, the crimson room bloomed with light. Tom and Miss Baker sat at\\neither end of the long couch and she read aloud to him from the\\nSaturday Evening Post—the words, murmurous and uninflected, running\\ntogether in a soothing tune. The lamplight, bright on his boots and\\ndull on the autumn-leaf yellow of her hair, glinted along the paper as\\nshe turned a page with a flutter of slender muscles in her arms.\\n\\nWhen we came in she held us silent for a moment with a lifted hand.\\n\\n“To be continued,” she said, tossing the magazine on the table, “in\\nour very next issue.”\\n\\nHer body asserted itself with a restless movement of her knee, and she\\nstood up.\\n\\n“Ten o’clock,” she remarked, apparently finding the time on the\\nceiling. “Time for this good girl to go to bed.”\\n\\n“Jordan’s going to play in the tournament tomorrow,” explained Daisy,\\n“over at Westchester.”\\n\\n“Oh—you’re Jordan Baker.”\\n\\nI knew now why her face was familiar—its pleasing contemptuous\\nexpression had looked out at me from many rotogravure pictures of the\\nsporting life at Asheville and Hot Springs and Palm Beach. I had heard\\nsome story of her too, a critical, unpleasant story, but what it was I\\nhad forgotten long ago.\\n\\n“Good night,” she said softly. “Wake me at eight, won’t you.”\\n\\n“If you’ll get up.”\\n\\n“I will. Good night, Mr. Carraway. See you anon.”\\n\\n“Of course you will,” confirmed Daisy. “In fact I think I’ll arrange a\\nmarriage. Come over often, Nick, and I’ll sort of—oh—fling you\\ntogether. You know—lock you up accidentally in linen closets and push\\nyou out to sea in a boat, and all that sort of thing—”\\n\\n“Good night,” called Miss Baker from the stairs. “I haven’t heard a\\nword.”\\n\\n“She’s a nice girl,” said Tom after a moment. “They oughtn’t to let\\nher run around the country this way.”\\n\\n“Who oughtn’t to?” inquired Daisy coldly.\\n\\n“Her family.”\\n\\n“Her family is one aunt about a thousand years old. Besides, Nick’s\\ngoing to look after her, aren’t you, Nick? She’s going to spend lots\\nof weekends out here this summer. I think the home influence will be\\nvery good for her.”\\n\\nDaisy and Tom looked at each other for a moment in silence.\\n\\n“Is she from New York?” I asked quickly.\\n\\n“From Louisville. Our white girlhood was passed together there. Our\\nbeautiful white—”\\n\\n“Did you give Nick a little heart to heart talk on the veranda?”\\ndemanded Tom suddenly.\\n\\n“Did I?” She looked at me. “I can’t seem to remember, but I think we\\ntalked about the Nordic race. Yes, I’m sure we did. It sort of crept\\nup on us and first thing you know—”\\n\\n“Don’t believe everything you hear, Nick,” he advised me.\\n', text_annotated='<narrator>Inside, the crimson room bloomed with light. Tom and Miss Baker sat at either end of the long couch and she read aloud to him from the Saturday Evening Post—the words, murmurous and uninflected, running together in a soothing tune. The lamplight, bright on his boots and dull on the autumn-leaf yellow of her hair, glinted along the paper as she turned a page with a flutter of slender muscles in her arms.</narrator>\\n\\n<narrator>When we came in she held us silent for a moment with a lifted hand.</narrator>\\n\\n<Jordan>“To be continued,”</Jordan> <narrator>she said, tossing the magazine on the table,</narrator> <Jordan>“in our very next issue.”</Jordan>\\n\\n<narrator>Her body asserted itself with a restless movement of her knee, and she stood up.</narrator>\\n\\n<Jordan>“Ten o’clock,”</Jordan> <narrator>she remarked, apparently finding the time on the ceiling.</narrator> <Jordan>“Time for this good girl to go to bed.”</Jordan>\\n\\n<Daisy>“Jordan’s going to play in the tournament tomorrow,”</Daisy> <narrator>explained Daisy,</narrator> <Daisy>“over at Westchester.”</Daisy>\\n\\n<narrator>“Oh—you’re Jordan Baker.”</narrator>\\n\\n<narrator>I knew now why her face was familiar—its pleasing contemptuous expression had looked out at me from many rotogravure pictures of the sporting life at Asheville and Hot Springs and Palm Beach. I had heard some story of her too, a critical, unpleasant story, but what it was I had forgotten long ago.</narrator>\\n\\n<Jordan>“Good night,”</Jordan> <narrator>she said softly.</narrator> <Jordan>“Wake me at eight, won’t you.”</Jordan>\\n\\n<Daisy>“If you’ll get up.”</Daisy>\\n\\n<Jordan>“I will. Good night, Mr. Carraway. See you anon.”</Jordan>\\n\\n<Daisy>“Of course you will,”</Daisy> <narrator>confirmed Daisy.</narrator> <Daisy>“In fact I think I’ll arrange a marriage. Come over often, Nick, and I’ll sort of—oh—fling you together. You know—lock you up accidentally in linen closets and push you out to sea in a boat, and all that sort of thing—”</Daisy>\\n\\n<Jordan>“Good night,”</Jordan> <narrator>called Miss Baker from the stairs.</narrator> <Jordan>“I haven’t heard a word.”</Jordan>\\n\\n<Tom>“She’s a nice girl,”</Tom> <narrator>said Tom after a moment.</narrator> <Tom>“They oughtn’t to let her run around the country this way.”</Tom>\\n\\n<Daisy>“Who oughtn’t to?”</Daisy> <narrator>inquired Daisy coldly.</narrator>\\n\\n<Tom>“Her family.”</Tom>\\n\\n<Daisy>“Her family is one aunt about a thousand years old. Besides, Nick’s going to look after her, aren’t you, Nick? She’s going to spend lots of weekends out here this summer. I think the home influence will be very good for her.”</Daisy>\\n\\n<narrator>Daisy and Tom looked at each other for a moment in silence.</narrator>\\n\\n<narrator>“Is she from New York?”</narrator> <narrator>I asked quickly.</narrator>\\n\\n<Daisy>“From Louisville. Our white girlhood was passed together there. Our beautiful white—”</Daisy>\\n\\n<Tom>“Did you give Nick a little heart to heart talk on the veranda?”</Tom> <narrator>demanded Tom suddenly.</narrator>\\n\\n<Daisy>“Did I?”</Daisy> <narrator>She looked at me.</narrator> <Daisy>“I can’t seem to remember, but I think we talked about the Nordic race. Yes, I’m sure we did. It sort of crept up on us and first thing you know—”</Daisy>\\n\\n<Tom>“Don’t believe everything you hear, Nick,”</Tom> <narrator>he advised me.</narrator>')"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Tom', 'Jordan', 'Daisy', 'narrator']"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res.characters"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<narrator>Inside, the crimson room bloomed with light. Tom and Miss Baker sat at either end of the long couch and she read aloud to him from the Saturday Evening Post—the words, murmurous and uninflected, running together in a soothing tune. The lamplight, bright on his boots and dull on the autumn-leaf yellow of her hair, glinted along the paper as she turned a page with a flutter of slender muscles in her arms.</narrator>\n",
"\n",
"<narrator>When we came in she held us silent for a moment with a lifted hand.</narrator>\n",
"\n",
"<Jordan>“To be continued,”</Jordan> <narrator>she said, tossing the magazine on the table,</narrator> <Jordan>“in our very next issue.”</Jordan>\n",
"\n",
"<narrator>Her body asserted itself with a restless movement of her knee, and she stood up.</narrator>\n",
"\n",
"<Jordan>“Ten o’clock,”</Jordan> <narrator>she remarked, apparently finding the time on the ceiling.</narrator> <Jordan>“Time for this good girl to go to bed.”</Jordan>\n",
"\n",
"<Daisy>“Jordan’s going to play in the tournament tomorrow,”</Daisy> <narrator>explained Daisy,</narrator> <Daisy>“over at Westchester.”</Daisy>\n",
"\n",
"<narrator>“Oh—you’re Jordan Baker.”</narrator>\n",
"\n",
"<narrator>I knew now why her face was familiar—its pleasing contemptuous expression had looked out at me from many rotogravure pictures of the sporting life at Asheville and Hot Springs and Palm Beach. I had heard some story of her too, a critical, unpleasant story, but what it was I had forgotten long ago.</narrator>\n",
"\n",
"<Jordan>“Good night,”</Jordan> <narrator>she said softly.</narrator> <Jordan>“Wake me at eight, won’t you.”</Jordan>\n",
"\n",
"<Daisy>“If you’ll get up.”</Daisy>\n",
"\n",
"<Jordan>“I will. Good night, Mr. Carraway. See you anon.”</Jordan>\n",
"\n",
"<Daisy>“Of course you will,”</Daisy> <narrator>confirmed Daisy.</narrator> <Daisy>“In fact I think I’ll arrange a marriage. Come over often, Nick, and I’ll sort of—oh—fling you together. You know—lock you up accidentally in linen closets and push you out to sea in a boat, and all that sort of thing—”</Daisy>\n",
"\n",
"<Jordan>“Good night,”</Jordan> <narrator>called Miss Baker from the stairs.</narrator> <Jordan>“I haven’t heard a word.”</Jordan>\n",
"\n",
"<Tom>“She’s a nice girl,”</Tom> <narrator>said Tom after a moment.</narrator> <Tom>“They oughtn’t to let her run around the country this way.”</Tom>\n",
"\n",
"<Daisy>“Who oughtn’t to?”</Daisy> <narrator>inquired Daisy coldly.</narrator>\n",
"\n",
"<Tom>“Her family.”</Tom>\n",
"\n",
"<Daisy>“Her family is one aunt about a thousand years old. Besides, Nick’s going to look after her, aren’t you, Nick? She’s going to spend lots of weekends out here this summer. I think the home influence will be very good for her.”</Daisy>\n",
"\n",
"<narrator>Daisy and Tom looked at each other for a moment in silence.</narrator>\n",
"\n",
"<narrator>“Is she from New York?”</narrator> <narrator>I asked quickly.</narrator>\n",
"\n",
"<Daisy>“From Louisville. Our white girlhood was passed together there. Our beautiful white—”</Daisy>\n",
"\n",
"<Tom>“Did you give Nick a little heart to heart talk on the veranda?”</Tom> <narrator>demanded Tom suddenly.</narrator>\n",
"\n",
"<Daisy>“Did I?”</Daisy> <narrator>She looked at me.</narrator> <Daisy>“I can’t seem to remember, but I think we talked about the Nordic race. Yes, I’m sure we did. It sort of crept up on us and first thing you know—”</Daisy>\n",
"\n",
"<Tom>“Don’t believe everything you hear, Nick,”</Tom> <narrator>he advised me.</narrator>\n"
]
}
],
"source": [
"print(res.text_annotated)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"characters: ['Tom', 'Jordan', 'Daisy', 'narrator']\n",
"--------------------\n",
"[narrator] Inside, the crimson room bloomed with light. Tom and Miss Baker sat at either end of the long couch and she read aloud to him from the Saturday Evening Post—the words, murmurous and uninflected, running together in a soothing tune. The lamplight, bright on his boots and dull on the autumn-leaf yellow of her hair, glinted along the paper as she turned a page with a flutter of slender muscles in her arms.\n",
"[narrator] When we came in she held us silent for a moment with a lifted hand.\n",
"[Jordan] “To be continued,”\n",
"[narrator] she said, tossing the magazine on the table,\n",
"[Jordan] “in our very next issue.”\n",
"[narrator] Her body asserted itself with a restless movement of her knee, and she stood up.\n",
"[Jordan] “Ten o’clock,”\n",
"[narrator] she remarked, apparently finding the time on the ceiling.\n",
"[Jordan] “Time for this good girl to go to bed.”\n",
"[Daisy] “Jordan’s going to play in the tournament tomorrow,”\n",
"[narrator] explained Daisy,\n",
"[Daisy] “over at Westchester.”\n",
"[narrator] “Oh—you’re Jordan Baker.”\n",
"[narrator] I knew now why her face was familiar—its pleasing contemptuous expression had looked out at me from many rotogravure pictures of the sporting life at Asheville and Hot Springs and Palm Beach. I had heard some story of her too, a critical, unpleasant story, but what it was I had forgotten long ago.\n",
"[Jordan] “Good night,”\n",
"[narrator] she said softly.\n",
"[Jordan] “Wake me at eight, won’t you.”\n",
"[Daisy] “If you’ll get up.”\n",
"[Jordan] “I will. Good night, Mr. Carraway. See you anon.”\n",
"[Daisy] “Of course you will,”\n",
"[narrator] confirmed Daisy.\n",
"[Daisy] “In fact I think I’ll arrange a marriage. Come over often, Nick, and I’ll sort of—oh—fling you together. You know—lock you up accidentally in linen closets and push you out to sea in a boat, and all that sort of thing—”\n",
"[Jordan] “Good night,”\n",
"[narrator] called Miss Baker from the stairs.\n",
"[Jordan] “I haven’t heard a word.”\n",
"[Tom] “She’s a nice girl,”\n",
"[narrator] said Tom after a moment.\n",
"[Tom] “They oughtn’t to let her run around the country this way.”\n",
"[Daisy] “Who oughtn’t to?”\n",
"[narrator] inquired Daisy coldly.\n",
"[Tom] “Her family.”\n",
"[Daisy] “Her family is one aunt about a thousand years old. Besides, Nick’s going to look after her, aren’t you, Nick? She’s going to spend lots of weekends out here this summer. I think the home influence will be very good for her.”\n",
"[narrator] Daisy and Tom looked at each other for a moment in silence.\n",
"[narrator] “Is she from New York?”\n",
"[narrator] I asked quickly.\n",
"[Daisy] “From Louisville. Our white girlhood was passed together there. Our beautiful white—”\n",
"[Tom] “Did you give Nick a little heart to heart talk on the veranda?”\n",
"[narrator] demanded Tom suddenly.\n",
"[Daisy] “Did I?”\n",
"[narrator] She looked at me.\n",
"[Daisy] “I can’t seem to remember, but I think we talked about the Nordic race. Yes, I’m sure we did. It sort of crept up on us and first thing you know—”\n",
"[Tom] “Don’t believe everything you hear, Nick,”\n",
"[narrator] he advised me.\n"
]
}
],
"source": [
"print(res.to_pretty_text())"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"LLM usage:\n",
"\n",
"Tokens Used: 1817\n",
"\tPrompt Tokens: 877\n",
"\tCompletion Tokens: 940\n",
"Successful Requests: 1\n",
"Total Cost (USD): $0.0115925\n"
]
}
],
"source": [
"print(f'LLM usage:\\n\\n{cb}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## map characters to voices"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"from src.select_voice_chain import create_voice_mapping_chain"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"chain = create_voice_mapping_chain(llm_model=GPTModels.GPT_4_TURBO_2024_04_09)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"ChatPromptTemplate(input_variables=['characters', 'text'], input_types={}, partial_variables={'available_genders': '\"male\", \"female\"', 'available_age_groups': '\"old\", \"middle_aged\", \"young\"', 'format_instructions': 'The output should be formatted as a JSON instance that conforms to the JSON schema below.\\n\\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\\n\\nHere is the output schema:\\n```\\n{\"$defs\": {\"CharacterProperties\": {\"properties\": {\"gender\": {\"title\": \"Gender\", \"type\": \"string\"}, \"age_group\": {\"title\": \"Age Group\", \"type\": \"string\"}}, \"required\": [\"gender\", \"age_group\"], \"title\": \"CharacterProperties\", \"type\": \"object\"}}, \"properties\": {\"character2props\": {\"additionalProperties\": {\"$ref\": \"#/$defs/CharacterProperties\"}, \"title\": \"Character2Props\", \"type\": \"object\"}}, \"required\": [\"character2props\"]}\\n```'}, messages=[SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=['available_age_groups', 'available_genders', 'format_instructions'], input_types={}, partial_variables={}, template='You are a helpful assistant proficient in literature and psychology.\\nOur goal is to create an audio book from the given text.\\nFor that we need to hire voice actors.\\nPlease help us to find the right actor for each character present in the text.\\n\\nYou are provided with the text split by the characters\\nto whom text parts belong to.\\n\\nYour task is to assign available properties to each character provided.\\nList of available properties:\\n- gender: {available_genders}\\n- age_group: {available_age_groups}\\n\\nNOTES:\\n- assign EXACTLY ONE property value for each property\\n- select properties values ONLY from the list of AVAILABLE property values\\n- fill properties for ALL characters from the list provided\\n- DO NOT include any characters absent in the list provided\\n\\n{format_instructions}\\n'), additional_kwargs={}), HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['characters', 'text'], input_types={}, partial_variables={}, template='<text>\\n{text}\\n</text>\\n\\n<characters>\\n{characters}\\n</characters>\\n'), additional_kwargs={})])\n",
"| RunnableBinding(bound=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x174a82d80>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x174a812e0>, root_client=<openai.OpenAI object at 0x174a82d50>, root_async_client=<openai.AsyncOpenAI object at 0x174a81730>, model_name='gpt-4-turbo-2024-04-09', temperature=0.0, model_kwargs={}, openai_api_key=SecretStr('**********'), request_timeout=Timeout(connect=4, read=60, write=60, pool=60)), kwargs={'response_format': {'type': 'json_object'}}, config={}, config_factories=[])\n",
"| PydanticOutputParser(pydantic_object=<class 'src.select_voice_chain.AllCharactersProperties'>)"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-10-10 02:37:46,347 [INFO] audio-books (lc_callbacks.py): call to gpt-4-turbo-2024-04-09 with 2 messages:\n",
"{'role': 'system', 'content': 'You are a helpful assistant proficient in literature and psychology.\\nOur goal is to create an audio book from the given text.\\nFor that we need to hire voice actors.\\nPlease help us to find the right actor for each character present in the text.\\n\\nYou are provided with the text split by the characters\\nto whom text parts belong to.\\n\\nYour task is to assign available properties to each character provided.\\nList of available properties:\\n- gender: \"male\", \"female\"\\n- age_group: \"old\", \"middle_aged\", \"young\"\\n\\nNOTES:\\n- assign EXACTLY ONE property value for each property\\n- select properties values ONLY from the list of AVAILABLE property values\\n- fill properties for ALL characters from the list provided\\n- DO NOT include any characters absent in the list provided\\n\\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\\n\\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\\n\\nHere is the output schema:\\n```\\n{\"$defs\": {\"CharacterProperties\": {\"properties\": {\"gender\": {\"title\": \"Gender\", \"type\": \"string\"}, \"age_group\": {\"title\": \"Age Group\", \"type\": \"string\"}}, \"required\": [\"gender\", \"age_group\"], \"title\": \"CharacterProperties\", \"type\": \"object\"}}, \"properties\": {\"character2props\": {\"additionalProperties\": {\"$ref\": \"#/$defs/CharacterProperties\"}, \"title\": \"Character2Props\", \"type\": \"object\"}}, \"required\": [\"character2props\"]}\\n```\\n'}\n",
"{'role': 'human', 'content': \"<text>\\n<narrator>Inside, the crimson room bloomed with light. Tom and Miss Baker sat at either end of the long couch and she read aloud to him from the Saturday Evening Post—the words, murmurous and uninflected, running together in a soothing tune. The lamplight, bright on his boots and dull on the autumn-leaf yellow of her hair, glinted along the paper as she turned a page with a flutter of slender muscles in her arms.</narrator>\\n\\n<narrator>When we came in she held us silent for a moment with a lifted hand.</narrator>\\n\\n<Jordan>“To be continued,”</Jordan> <narrator>she said, tossing the magazine on the table,</narrator> <Jordan>“in our very next issue.”</Jordan>\\n\\n<narrator>Her body asserted itself with a restless movement of her knee, and she stood up.</narrator>\\n\\n<Jordan>“Ten o’clock,”</Jordan> <narrator>she remarked, apparently finding the time on the ceiling.</narrator> <Jordan>“Time for this good girl to go to bed.”</Jordan>\\n\\n<Daisy>“Jordan’s going to play in the tournament tomorrow,”</Daisy> <narrator>explained Daisy,</narrator> <Daisy>“over at Westchester.”</Daisy>\\n\\n<narrator>“Oh—you’re Jordan Baker.”</narrator>\\n\\n<narrator>I knew now why her face was familiar—its pleasing contemptuous expression had looked out at me from many rotogravure pictures of the sporting life at Asheville and Hot Springs and Palm Beach. I had heard some story of her too, a critical, unpleasant story, but what it was I had forgotten long ago.</narrator>\\n\\n<Jordan>“Good night,”</Jordan> <narrator>she said softly.</narrator> <Jordan>“Wake me at eight, won’t you.”</Jordan>\\n\\n<Daisy>“If you’ll get up.”</Daisy>\\n\\n<Jordan>“I will. Good night, Mr. Carraway. See you anon.”</Jordan>\\n\\n<Daisy>“Of course you will,”</Daisy> <narrator>confirmed Daisy.</narrator> <Daisy>“In fact I think I’ll arrange a marriage. Come over often, Nick, and I’ll sort of—oh—fling you together. You know—lock you up accidentally in linen closets and push you out to sea in a boat, and all that sort of thing—”</Daisy>\\n\\n<Jordan>“Good night,”</Jordan> <narrator>called Miss Baker from the stairs.</narrator> <Jordan>“I haven’t heard a word.”</Jordan>\\n\\n<Tom>“She’s a nice girl,”</Tom> <narrator>said Tom after a moment.</narrator> <Tom>“They oughtn’t to let her run around the country this way.”</Tom>\\n\\n<Daisy>“Who oughtn’t to?”</Daisy> <narrator>inquired Daisy coldly.</narrator>\\n\\n<Tom>“Her family.”</Tom>\\n\\n<Daisy>“Her family is one aunt about a thousand years old. Besides, Nick’s going to look after her, aren’t you, Nick? She’s going to spend lots of weekends out here this summer. I think the home influence will be very good for her.”</Daisy>\\n\\n<narrator>Daisy and Tom looked at each other for a moment in silence.</narrator>\\n\\n<narrator>“Is she from New York?”</narrator> <narrator>I asked quickly.</narrator>\\n\\n<Daisy>“From Louisville. Our white girlhood was passed together there. Our beautiful white—”</Daisy>\\n\\n<Tom>“Did you give Nick a little heart to heart talk on the veranda?”</Tom> <narrator>demanded Tom suddenly.</narrator>\\n\\n<Daisy>“Did I?”</Daisy> <narrator>She looked at me.</narrator> <Daisy>“I can’t seem to remember, but I think we talked about the Nordic race. Yes, I’m sure we did. It sort of crept up on us and first thing you know—”</Daisy>\\n\\n<Tom>“Don’t believe everything you hear, Nick,”</Tom> <narrator>he advised me.</narrator>\\n</text>\\n\\n<characters>\\n['Tom', 'Jordan', 'Daisy', 'narrator']\\n</characters>\\n\"}\n",
"2024-10-10 02:37:52,060 [INFO] httpx (_client.py): HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n",
"2024-10-10 02:37:52,063 [INFO] audio-books (lc_callbacks.py): raw LLM response: \"{\n",
" \"character2props\": {\n",
" \"Tom\": {\n",
" \"gender\": \"male\",\n",
" \"age_group\": \"middle_aged\"\n",
" },\n",
" \"Jordan\": {\n",
" \"gender\": \"female\",\n",
" \"age_group\": \"young\"\n",
" },\n",
" \"Daisy\": {\n",
" \"gender\": \"female\",\n",
" \"age_group\": \"young\"\n",
" },\n",
" \"narrator\": {\n",
" \"gender\": \"male\",\n",
" \"age_group\": \"middle_aged\"\n",
" }\n",
" }\n",
"}\"\n"
]
}
],
"source": [
"res2 = chain.invoke(\n",
" {\"text\": res.text_annotated, \"characters\": res.characters},\n",
" config={\"callbacks\": [LCMessageLoggerAsync()]},\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AllCharactersProperties(character2props={'Tom': CharacterProperties(gender='male', age_group='middle_aged'), 'Jordan': CharacterProperties(gender='female', age_group='young'), 'Daisy': CharacterProperties(gender='female', age_group='young'), 'narrator': CharacterProperties(gender='male', age_group='middle_aged')})"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 22 entries, 0 to 21\n",
"Data columns (total 14 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 voice_id 22 non-null object \n",
" 1 name 22 non-null object \n",
" 2 preview_url 22 non-null object \n",
" 3 owner_id 0 non-null float64\n",
" 4 permission_on_resource 2 non-null object \n",
" 5 is_legacy 22 non-null bool \n",
" 6 is_mixed 22 non-null bool \n",
" 7 accent 22 non-null object \n",
" 8 description 20 non-null object \n",
" 9 age 22 non-null object \n",
" 10 gender 22 non-null object \n",
" 11 category 22 non-null object \n",
" 12 language 2 non-null object \n",
" 13 descriptive 2 non-null object \n",
"dtypes: bool(2), float64(1), object(11)\n",
"memory usage: 2.2+ KB\n"
]
}
],
"source": [
"voices = pd.read_csv(\"11labs_available_tts_voices.csv\")\n",
"voices.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['middle_aged', 'young', 'old'], dtype=object)"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"voices[\"age\"].unique()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['female', 'male', 'non-binary', 'neutral'], dtype=object)"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"voices[\"gender\"].unique()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "ai-audio-books",
"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": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|