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 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091
// This file is @generated by prost-build.
/// A set of words or phrases that represents a common concept likely to appear
/// in your audio, for example a list of passenger ship names. CustomClass items
/// can be substituted into placeholders that you set in PhraseSet phrases.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct CustomClass {
/// The resource name of the custom class.
#[prost(string, tag = "1")]
pub name: ::prost::alloc::string::String,
/// If this custom class is a resource, the custom_class_id is the resource id
/// of the CustomClass. Case sensitive.
#[prost(string, tag = "2")]
pub custom_class_id: ::prost::alloc::string::String,
/// A collection of class items.
#[prost(message, repeated, tag = "3")]
pub items: ::prost::alloc::vec::Vec<custom_class::ClassItem>,
}
/// Nested message and enum types in `CustomClass`.
pub mod custom_class {
/// An item of the class.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ClassItem {
/// The class item's value.
#[prost(string, tag = "1")]
pub value: ::prost::alloc::string::String,
}
}
/// Provides "hints" to the speech recognizer to favor specific words and phrases
/// in the results.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct PhraseSet {
/// The resource name of the phrase set.
#[prost(string, tag = "1")]
pub name: ::prost::alloc::string::String,
/// A list of word and phrases.
#[prost(message, repeated, tag = "2")]
pub phrases: ::prost::alloc::vec::Vec<phrase_set::Phrase>,
/// Hint Boost. Positive value will increase the probability that a specific
/// phrase will be recognized over other similar sounding phrases. The higher
/// the boost, the higher the chance of false positive recognition as well.
/// Negative boost values would correspond to anti-biasing. Anti-biasing is not
/// enabled, so negative boost will simply be ignored. Though `boost` can
/// accept a wide range of positive values, most use cases are best served with
/// values between 0 (exclusive) and 20. We recommend using a binary search
/// approach to finding the optimal value for your use case as well as adding
/// phrases both with and without boost to your requests.
#[prost(float, tag = "4")]
pub boost: f32,
}
/// Nested message and enum types in `PhraseSet`.
pub mod phrase_set {
/// A phrases containing words and phrase "hints" so that
/// the speech recognition is more likely to recognize them. This can be used
/// to improve the accuracy for specific words and phrases, for example, if
/// specific commands are typically spoken by the user. This can also be used
/// to add additional words to the vocabulary of the recognizer. See
/// [usage limits](<https://cloud.google.com/speech-to-text/quotas#content>).
///
/// List items can also include pre-built or custom classes containing groups
/// of words that represent common concepts that occur in natural language. For
/// example, rather than providing a phrase hint for every month of the
/// year (e.g. "i was born in january", "i was born in febuary", ...), use the
/// pre-built `$MONTH` class improves the likelihood of correctly transcribing
/// audio that includes months (e.g. "i was born in $month").
/// To refer to pre-built classes, use the class' symbol prepended with `$`
/// e.g. `$MONTH`. To refer to custom classes that were defined inline in the
/// request, set the class's `custom_class_id` to a string unique to all class
/// resources and inline classes. Then use the class' id wrapped in $`{...}`
/// e.g. "${my-months}". To refer to custom classes resources, use the class'
/// id wrapped in `${}` (e.g. `${my-months}`).
///
/// Speech-to-Text supports three locations: `global`, `us` (US North America),
/// and `eu` (Europe). If you are calling the `speech.googleapis.com`
/// endpoint, use the `global` location. To specify a region, use a
/// [regional endpoint](<https://cloud.google.com/speech-to-text/docs/endpoints>)
/// with matching `us` or `eu` location value.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Phrase {
/// The phrase itself.
#[prost(string, tag = "1")]
pub value: ::prost::alloc::string::String,
/// Hint Boost. Overrides the boost set at the phrase set level.
/// Positive value will increase the probability that a specific phrase will
/// be recognized over other similar sounding phrases. The higher the boost,
/// the higher the chance of false positive recognition as well. Negative
/// boost will simply be ignored. Though `boost` can accept a wide range of
/// positive values, most use cases are best served
/// with values between 0 and 20. We recommend using a binary search approach
/// to finding the optimal value for your use case as well as adding
/// phrases both with and without boost to your requests.
#[prost(float, tag = "2")]
pub boost: f32,
}
}
/// Speech adaptation configuration.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SpeechAdaptation {
/// A collection of phrase sets. To specify the hints inline, leave the
/// phrase set's `name` blank and fill in the rest of its fields. Any
/// phrase set can use any custom class.
#[prost(message, repeated, tag = "1")]
pub phrase_sets: ::prost::alloc::vec::Vec<PhraseSet>,
/// A collection of phrase set resource names to use.
#[prost(string, repeated, tag = "2")]
pub phrase_set_references: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
/// A collection of custom classes. To specify the classes inline, leave the
/// class' `name` blank and fill in the rest of its fields, giving it a unique
/// `custom_class_id`. Refer to the inline defined class in phrase hints by its
/// `custom_class_id`.
#[prost(message, repeated, tag = "3")]
pub custom_classes: ::prost::alloc::vec::Vec<CustomClass>,
/// Augmented Backus-Naur form (ABNF) is a standardized grammar notation
/// comprised by a set of derivation rules.
/// See specifications: <https://www.w3.org/TR/speech-grammar>
#[prost(message, optional, tag = "4")]
pub abnf_grammar: ::core::option::Option<speech_adaptation::AbnfGrammar>,
}
/// Nested message and enum types in `SpeechAdaptation`.
pub mod speech_adaptation {
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct AbnfGrammar {
/// All declarations and rules of an ABNF grammar broken up into multiple
/// strings that will end up concatenated.
#[prost(string, repeated, tag = "1")]
pub abnf_strings: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
}
}
/// Transcription normalization configuration. Use transcription normalization
/// to automatically replace parts of the transcript with phrases of your
/// choosing. For StreamingRecognize, this normalization only applies to stable
/// partial transcripts (stability > 0.8) and final transcripts.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TranscriptNormalization {
/// A list of replacement entries. We will perform replacement with one entry
/// at a time. For example, the second entry in ["cat" => "dog", "mountain cat"
/// => "mountain dog"] will never be applied because we will always process the
/// first entry before it. At most 100 entries.
#[prost(message, repeated, tag = "1")]
pub entries: ::prost::alloc::vec::Vec<transcript_normalization::Entry>,
}
/// Nested message and enum types in `TranscriptNormalization`.
pub mod transcript_normalization {
/// A single replacement configuration.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Entry {
/// What to replace. Max length is 100 characters.
#[prost(string, tag = "1")]
pub search: ::prost::alloc::string::String,
/// What to replace with. Max length is 100 characters.
#[prost(string, tag = "2")]
pub replace: ::prost::alloc::string::String,
/// Whether the search is case sensitive.
#[prost(bool, tag = "3")]
pub case_sensitive: bool,
}
}
/// Message sent by the client for the `CreatePhraseSet` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct CreatePhraseSetRequest {
/// Required. The parent resource where this phrase set will be created.
/// Format:
///
/// `projects/{project}/locations/{location}`
///
/// Speech-to-Text supports three locations: `global`, `us` (US North America),
/// and `eu` (Europe). If you are calling the `speech.googleapis.com`
/// endpoint, use the `global` location. To specify a region, use a
/// [regional endpoint](<https://cloud.google.com/speech-to-text/docs/endpoints>)
/// with matching `us` or `eu` location value.
#[prost(string, tag = "1")]
pub parent: ::prost::alloc::string::String,
/// Required. The ID to use for the phrase set, which will become the final
/// component of the phrase set's resource name.
///
/// This value should restrict to letters, numbers, and hyphens, with the first
/// character a letter, the last a letter or a number, and be 4-63 characters.
#[prost(string, tag = "2")]
pub phrase_set_id: ::prost::alloc::string::String,
/// Required. The phrase set to create.
#[prost(message, optional, tag = "3")]
pub phrase_set: ::core::option::Option<PhraseSet>,
}
/// Message sent by the client for the `UpdatePhraseSet` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct UpdatePhraseSetRequest {
/// Required. The phrase set to update.
///
/// The phrase set's `name` field is used to identify the set to be
/// updated. Format:
///
/// `projects/{project}/locations/{location}/phraseSets/{phrase_set}`
///
/// Speech-to-Text supports three locations: `global`, `us` (US North America),
/// and `eu` (Europe). If you are calling the `speech.googleapis.com`
/// endpoint, use the `global` location. To specify a region, use a
/// [regional endpoint](<https://cloud.google.com/speech-to-text/docs/endpoints>)
/// with matching `us` or `eu` location value.
#[prost(message, optional, tag = "1")]
pub phrase_set: ::core::option::Option<PhraseSet>,
/// The list of fields to be updated.
#[prost(message, optional, tag = "2")]
pub update_mask: ::core::option::Option<::prost_types::FieldMask>,
}
/// Message sent by the client for the `GetPhraseSet` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct GetPhraseSetRequest {
/// Required. The name of the phrase set to retrieve. Format:
///
/// `projects/{project}/locations/{location}/phraseSets/{phrase_set}`
///
/// Speech-to-Text supports three locations: `global`, `us` (US North America),
/// and `eu` (Europe). If you are calling the `speech.googleapis.com`
/// endpoint, use the `global` location. To specify a region, use a
/// [regional endpoint](<https://cloud.google.com/speech-to-text/docs/endpoints>)
/// with matching `us` or `eu` location value.
#[prost(string, tag = "1")]
pub name: ::prost::alloc::string::String,
}
/// Message sent by the client for the `ListPhraseSet` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ListPhraseSetRequest {
/// Required. The parent, which owns this collection of phrase set. Format:
///
/// `projects/{project}/locations/{location}`
///
/// Speech-to-Text supports three locations: `global`, `us` (US North America),
/// and `eu` (Europe). If you are calling the `speech.googleapis.com`
/// endpoint, use the `global` location. To specify a region, use a
/// [regional endpoint](<https://cloud.google.com/speech-to-text/docs/endpoints>)
/// with matching `us` or `eu` location value.
#[prost(string, tag = "1")]
pub parent: ::prost::alloc::string::String,
/// The maximum number of phrase sets to return. The service may return
/// fewer than this value. If unspecified, at most 50 phrase sets will be
/// returned. The maximum value is 1000; values above 1000 will be coerced to
/// 1000.
#[prost(int32, tag = "2")]
pub page_size: i32,
/// A page token, received from a previous `ListPhraseSet` call.
/// Provide this to retrieve the subsequent page.
///
/// When paginating, all other parameters provided to `ListPhraseSet` must
/// match the call that provided the page token.
#[prost(string, tag = "3")]
pub page_token: ::prost::alloc::string::String,
}
/// Message returned to the client by the `ListPhraseSet` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ListPhraseSetResponse {
/// The phrase set.
#[prost(message, repeated, tag = "1")]
pub phrase_sets: ::prost::alloc::vec::Vec<PhraseSet>,
/// A token, which can be sent as `page_token` to retrieve the next page.
/// If this field is omitted, there are no subsequent pages.
#[prost(string, tag = "2")]
pub next_page_token: ::prost::alloc::string::String,
}
/// Message sent by the client for the `DeletePhraseSet` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct DeletePhraseSetRequest {
/// Required. The name of the phrase set to delete. Format:
///
/// `projects/{project}/locations/{location}/phraseSets/{phrase_set}`
#[prost(string, tag = "1")]
pub name: ::prost::alloc::string::String,
}
/// Message sent by the client for the `CreateCustomClass` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct CreateCustomClassRequest {
/// Required. The parent resource where this custom class will be created.
/// Format:
///
/// `projects/{project}/locations/{location}/customClasses`
///
/// Speech-to-Text supports three locations: `global`, `us` (US North America),
/// and `eu` (Europe). If you are calling the `speech.googleapis.com`
/// endpoint, use the `global` location. To specify a region, use a
/// [regional endpoint](<https://cloud.google.com/speech-to-text/docs/endpoints>)
/// with matching `us` or `eu` location value.
#[prost(string, tag = "1")]
pub parent: ::prost::alloc::string::String,
/// Required. The ID to use for the custom class, which will become the final
/// component of the custom class' resource name.
///
/// This value should restrict to letters, numbers, and hyphens, with the first
/// character a letter, the last a letter or a number, and be 4-63 characters.
#[prost(string, tag = "2")]
pub custom_class_id: ::prost::alloc::string::String,
/// Required. The custom class to create.
#[prost(message, optional, tag = "3")]
pub custom_class: ::core::option::Option<CustomClass>,
}
/// Message sent by the client for the `UpdateCustomClass` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct UpdateCustomClassRequest {
/// Required. The custom class to update.
///
/// The custom class's `name` field is used to identify the custom class to be
/// updated. Format:
///
/// `projects/{project}/locations/{location}/customClasses/{custom_class}`
///
/// Speech-to-Text supports three locations: `global`, `us` (US North America),
/// and `eu` (Europe). If you are calling the `speech.googleapis.com`
/// endpoint, use the `global` location. To specify a region, use a
/// [regional endpoint](<https://cloud.google.com/speech-to-text/docs/endpoints>)
/// with matching `us` or `eu` location value.
#[prost(message, optional, tag = "1")]
pub custom_class: ::core::option::Option<CustomClass>,
/// The list of fields to be updated.
#[prost(message, optional, tag = "2")]
pub update_mask: ::core::option::Option<::prost_types::FieldMask>,
}
/// Message sent by the client for the `GetCustomClass` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct GetCustomClassRequest {
/// Required. The name of the custom class to retrieve. Format:
///
/// `projects/{project}/locations/{location}/customClasses/{custom_class}`
#[prost(string, tag = "1")]
pub name: ::prost::alloc::string::String,
}
/// Message sent by the client for the `ListCustomClasses` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ListCustomClassesRequest {
/// Required. The parent, which owns this collection of custom classes. Format:
///
/// `projects/{project}/locations/{location}/customClasses`
///
/// Speech-to-Text supports three locations: `global`, `us` (US North America),
/// and `eu` (Europe). If you are calling the `speech.googleapis.com`
/// endpoint, use the `global` location. To specify a region, use a
/// [regional endpoint](<https://cloud.google.com/speech-to-text/docs/endpoints>)
/// with matching `us` or `eu` location value.
#[prost(string, tag = "1")]
pub parent: ::prost::alloc::string::String,
/// The maximum number of custom classes to return. The service may return
/// fewer than this value. If unspecified, at most 50 custom classes will be
/// returned. The maximum value is 1000; values above 1000 will be coerced to
/// 1000.
#[prost(int32, tag = "2")]
pub page_size: i32,
/// A page token, received from a previous `ListCustomClass` call.
/// Provide this to retrieve the subsequent page.
///
/// When paginating, all other parameters provided to `ListCustomClass` must
/// match the call that provided the page token.
#[prost(string, tag = "3")]
pub page_token: ::prost::alloc::string::String,
}
/// Message returned to the client by the `ListCustomClasses` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ListCustomClassesResponse {
/// The custom classes.
#[prost(message, repeated, tag = "1")]
pub custom_classes: ::prost::alloc::vec::Vec<CustomClass>,
/// A token, which can be sent as `page_token` to retrieve the next page.
/// If this field is omitted, there are no subsequent pages.
#[prost(string, tag = "2")]
pub next_page_token: ::prost::alloc::string::String,
}
/// Message sent by the client for the `DeleteCustomClass` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct DeleteCustomClassRequest {
/// Required. The name of the custom class to delete. Format:
///
/// `projects/{project}/locations/{location}/customClasses/{custom_class}`
///
/// Speech-to-Text supports three locations: `global`, `us` (US North America),
/// and `eu` (Europe). If you are calling the `speech.googleapis.com`
/// endpoint, use the `global` location. To specify a region, use a
/// [regional endpoint](<https://cloud.google.com/speech-to-text/docs/endpoints>)
/// with matching `us` or `eu` location value.
#[prost(string, tag = "1")]
pub name: ::prost::alloc::string::String,
}
/// Generated client implementations.
pub mod adaptation_client {
#![allow(unused_variables, dead_code, missing_docs, clippy::let_unit_value)]
use tonic::codegen::*;
use tonic::codegen::http::Uri;
/// Service that implements Google Cloud Speech Adaptation API.
#[derive(Debug, Clone)]
pub struct AdaptationClient<T> {
inner: tonic::client::Grpc<T>,
}
impl<T> AdaptationClient<T>
where
T: tonic::client::GrpcService<tonic::body::BoxBody>,
T::Error: Into<StdError>,
T::ResponseBody: Body<Data = Bytes> + std::marker::Send + 'static,
<T::ResponseBody as Body>::Error: Into<StdError> + std::marker::Send,
{
pub fn new(inner: T) -> Self {
let inner = tonic::client::Grpc::new(inner);
Self { inner }
}
pub fn with_origin(inner: T, origin: Uri) -> Self {
let inner = tonic::client::Grpc::with_origin(inner, origin);
Self { inner }
}
pub fn with_interceptor<F>(
inner: T,
interceptor: F,
) -> AdaptationClient<InterceptedService<T, F>>
where
F: tonic::service::Interceptor,
T::ResponseBody: Default,
T: tonic::codegen::Service<
http::Request<tonic::body::BoxBody>,
Response = http::Response<
<T as tonic::client::GrpcService<tonic::body::BoxBody>>::ResponseBody,
>,
>,
<T as tonic::codegen::Service<
http::Request<tonic::body::BoxBody>,
>>::Error: Into<StdError> + std::marker::Send + std::marker::Sync,
{
AdaptationClient::new(InterceptedService::new(inner, interceptor))
}
/// Compress requests with the given encoding.
///
/// This requires the server to support it otherwise it might respond with an
/// error.
#[must_use]
pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.send_compressed(encoding);
self
}
/// Enable decompressing responses.
#[must_use]
pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.accept_compressed(encoding);
self
}
/// Limits the maximum size of a decoded message.
///
/// Default: `4MB`
#[must_use]
pub fn max_decoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_decoding_message_size(limit);
self
}
/// Limits the maximum size of an encoded message.
///
/// Default: `usize::MAX`
#[must_use]
pub fn max_encoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_encoding_message_size(limit);
self
}
/// Create a set of phrase hints. Each item in the set can be a single word or
/// a multi-word phrase. The items in the PhraseSet are favored by the
/// recognition model when you send a call that includes the PhraseSet.
pub async fn create_phrase_set(
&mut self,
request: impl tonic::IntoRequest<super::CreatePhraseSetRequest>,
) -> std::result::Result<tonic::Response<super::PhraseSet>, tonic::Status> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/CreatePhraseSet",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Adaptation",
"CreatePhraseSet",
),
);
self.inner.unary(req, path, codec).await
}
/// Get a phrase set.
pub async fn get_phrase_set(
&mut self,
request: impl tonic::IntoRequest<super::GetPhraseSetRequest>,
) -> std::result::Result<tonic::Response<super::PhraseSet>, tonic::Status> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/GetPhraseSet",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new("google.cloud.speech.v1.Adaptation", "GetPhraseSet"),
);
self.inner.unary(req, path, codec).await
}
/// List phrase sets.
pub async fn list_phrase_set(
&mut self,
request: impl tonic::IntoRequest<super::ListPhraseSetRequest>,
) -> std::result::Result<
tonic::Response<super::ListPhraseSetResponse>,
tonic::Status,
> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/ListPhraseSet",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new("google.cloud.speech.v1.Adaptation", "ListPhraseSet"),
);
self.inner.unary(req, path, codec).await
}
/// Update a phrase set.
pub async fn update_phrase_set(
&mut self,
request: impl tonic::IntoRequest<super::UpdatePhraseSetRequest>,
) -> std::result::Result<tonic::Response<super::PhraseSet>, tonic::Status> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/UpdatePhraseSet",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Adaptation",
"UpdatePhraseSet",
),
);
self.inner.unary(req, path, codec).await
}
/// Delete a phrase set.
pub async fn delete_phrase_set(
&mut self,
request: impl tonic::IntoRequest<super::DeletePhraseSetRequest>,
) -> std::result::Result<tonic::Response<()>, tonic::Status> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/DeletePhraseSet",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Adaptation",
"DeletePhraseSet",
),
);
self.inner.unary(req, path, codec).await
}
/// Create a custom class.
pub async fn create_custom_class(
&mut self,
request: impl tonic::IntoRequest<super::CreateCustomClassRequest>,
) -> std::result::Result<tonic::Response<super::CustomClass>, tonic::Status> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/CreateCustomClass",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Adaptation",
"CreateCustomClass",
),
);
self.inner.unary(req, path, codec).await
}
/// Get a custom class.
pub async fn get_custom_class(
&mut self,
request: impl tonic::IntoRequest<super::GetCustomClassRequest>,
) -> std::result::Result<tonic::Response<super::CustomClass>, tonic::Status> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/GetCustomClass",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Adaptation",
"GetCustomClass",
),
);
self.inner.unary(req, path, codec).await
}
/// List custom classes.
pub async fn list_custom_classes(
&mut self,
request: impl tonic::IntoRequest<super::ListCustomClassesRequest>,
) -> std::result::Result<
tonic::Response<super::ListCustomClassesResponse>,
tonic::Status,
> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/ListCustomClasses",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Adaptation",
"ListCustomClasses",
),
);
self.inner.unary(req, path, codec).await
}
/// Update a custom class.
pub async fn update_custom_class(
&mut self,
request: impl tonic::IntoRequest<super::UpdateCustomClassRequest>,
) -> std::result::Result<tonic::Response<super::CustomClass>, tonic::Status> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/UpdateCustomClass",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Adaptation",
"UpdateCustomClass",
),
);
self.inner.unary(req, path, codec).await
}
/// Delete a custom class.
pub async fn delete_custom_class(
&mut self,
request: impl tonic::IntoRequest<super::DeleteCustomClassRequest>,
) -> std::result::Result<tonic::Response<()>, tonic::Status> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Adaptation/DeleteCustomClass",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Adaptation",
"DeleteCustomClass",
),
);
self.inner.unary(req, path, codec).await
}
}
}
/// The top-level message sent by the client for the `Recognize` method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RecognizeRequest {
/// Required. Provides information to the recognizer that specifies how to
/// process the request.
#[prost(message, optional, tag = "1")]
pub config: ::core::option::Option<RecognitionConfig>,
/// Required. The audio data to be recognized.
#[prost(message, optional, tag = "2")]
pub audio: ::core::option::Option<RecognitionAudio>,
}
/// The top-level message sent by the client for the `LongRunningRecognize`
/// method.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct LongRunningRecognizeRequest {
/// Required. Provides information to the recognizer that specifies how to
/// process the request.
#[prost(message, optional, tag = "1")]
pub config: ::core::option::Option<RecognitionConfig>,
/// Required. The audio data to be recognized.
#[prost(message, optional, tag = "2")]
pub audio: ::core::option::Option<RecognitionAudio>,
/// Optional. Specifies an optional destination for the recognition results.
#[prost(message, optional, tag = "4")]
pub output_config: ::core::option::Option<TranscriptOutputConfig>,
}
/// Specifies an optional destination for the recognition results.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TranscriptOutputConfig {
#[prost(oneof = "transcript_output_config::OutputType", tags = "1")]
pub output_type: ::core::option::Option<transcript_output_config::OutputType>,
}
/// Nested message and enum types in `TranscriptOutputConfig`.
pub mod transcript_output_config {
#[derive(Clone, PartialEq, ::prost::Oneof)]
pub enum OutputType {
/// Specifies a Cloud Storage URI for the recognition results. Must be
/// specified in the format: `gs://bucket_name/object_name`, and the bucket
/// must already exist.
#[prost(string, tag = "1")]
GcsUri(::prost::alloc::string::String),
}
}
/// The top-level message sent by the client for the `StreamingRecognize` method.
/// Multiple `StreamingRecognizeRequest` messages are sent. The first message
/// must contain a `streaming_config` message and must not contain
/// `audio_content`. All subsequent messages must contain `audio_content` and
/// must not contain a `streaming_config` message.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct StreamingRecognizeRequest {
/// The streaming request, which is either a streaming config or audio content.
#[prost(oneof = "streaming_recognize_request::StreamingRequest", tags = "1, 2")]
pub streaming_request: ::core::option::Option<
streaming_recognize_request::StreamingRequest,
>,
}
/// Nested message and enum types in `StreamingRecognizeRequest`.
pub mod streaming_recognize_request {
/// The streaming request, which is either a streaming config or audio content.
#[derive(Clone, PartialEq, ::prost::Oneof)]
pub enum StreamingRequest {
/// Provides information to the recognizer that specifies how to process the
/// request. The first `StreamingRecognizeRequest` message must contain a
/// `streaming_config` message.
#[prost(message, tag = "1")]
StreamingConfig(super::StreamingRecognitionConfig),
/// The audio data to be recognized. Sequential chunks of audio data are sent
/// in sequential `StreamingRecognizeRequest` messages. The first
/// `StreamingRecognizeRequest` message must not contain `audio_content` data
/// and all subsequent `StreamingRecognizeRequest` messages must contain
/// `audio_content` data. The audio bytes must be encoded as specified in
/// `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a
/// pure binary representation (not base64). See
/// [content limits](<https://cloud.google.com/speech-to-text/quotas#content>).
#[prost(bytes, tag = "2")]
AudioContent(::prost::bytes::Bytes),
}
}
/// Provides information to the recognizer that specifies how to process the
/// request.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct StreamingRecognitionConfig {
/// Required. Provides information to the recognizer that specifies how to
/// process the request.
#[prost(message, optional, tag = "1")]
pub config: ::core::option::Option<RecognitionConfig>,
/// If `false` or omitted, the recognizer will perform continuous
/// recognition (continuing to wait for and process audio even if the user
/// pauses speaking) until the client closes the input stream (gRPC API) or
/// until the maximum time limit has been reached. May return multiple
/// `StreamingRecognitionResult`s with the `is_final` flag set to `true`.
///
/// If `true`, the recognizer will detect a single spoken utterance. When it
/// detects that the user has paused or stopped speaking, it will return an
/// `END_OF_SINGLE_UTTERANCE` event and cease recognition. It will return no
/// more than one `StreamingRecognitionResult` with the `is_final` flag set to
/// `true`.
///
/// The `single_utterance` field can only be used with specified models,
/// otherwise an error is thrown. The `model` field in [`RecognitionConfig`][]
/// must be set to:
///
/// * `command_and_search`
/// * `phone_call` AND additional field `useEnhanced`=`true`
/// * The `model` field is left undefined. In this case the API auto-selects
/// a model based on any other parameters that you set in
/// `RecognitionConfig`.
#[prost(bool, tag = "2")]
pub single_utterance: bool,
/// If `true`, interim results (tentative hypotheses) may be
/// returned as they become available (these interim results are indicated with
/// the `is_final=false` flag).
/// If `false` or omitted, only `is_final=true` result(s) are returned.
#[prost(bool, tag = "3")]
pub interim_results: bool,
/// If `true`, responses with voice activity speech events will be returned as
/// they are detected.
#[prost(bool, tag = "5")]
pub enable_voice_activity_events: bool,
/// If set, the server will automatically close the stream after the specified
/// duration has elapsed after the last VOICE_ACTIVITY speech event has been
/// sent. The field `voice_activity_events` must also be set to true.
#[prost(message, optional, tag = "6")]
pub voice_activity_timeout: ::core::option::Option<
streaming_recognition_config::VoiceActivityTimeout,
>,
}
/// Nested message and enum types in `StreamingRecognitionConfig`.
pub mod streaming_recognition_config {
/// Events that a timeout can be set on for voice activity.
#[derive(Clone, Copy, PartialEq, ::prost::Message)]
pub struct VoiceActivityTimeout {
/// Duration to timeout the stream if no speech begins.
#[prost(message, optional, tag = "1")]
pub speech_start_timeout: ::core::option::Option<::prost_types::Duration>,
/// Duration to timeout the stream after speech ends.
#[prost(message, optional, tag = "2")]
pub speech_end_timeout: ::core::option::Option<::prost_types::Duration>,
}
}
/// Provides information to the recognizer that specifies how to process the
/// request.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RecognitionConfig {
/// Encoding of audio data sent in all `RecognitionAudio` messages.
/// This field is optional for `FLAC` and `WAV` audio files and required
/// for all other audio formats. For details, see
/// [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
#[prost(enumeration = "recognition_config::AudioEncoding", tag = "1")]
pub encoding: i32,
/// Sample rate in Hertz of the audio data sent in all
/// `RecognitionAudio` messages. Valid values are: 8000-48000.
/// 16000 is optimal. For best results, set the sampling rate of the audio
/// source to 16000 Hz. If that's not possible, use the native sample rate of
/// the audio source (instead of re-sampling).
/// This field is optional for FLAC and WAV audio files, but is
/// required for all other audio formats. For details, see
/// [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
#[prost(int32, tag = "2")]
pub sample_rate_hertz: i32,
/// The number of channels in the input audio data.
/// ONLY set this for MULTI-CHANNEL recognition.
/// Valid values for LINEAR16, OGG_OPUS and FLAC are `1`-`8`.
/// Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
/// If `0` or omitted, defaults to one channel (mono).
/// Note: We only recognize the first channel by default.
/// To perform independent recognition on each channel set
/// `enable_separate_recognition_per_channel` to 'true'.
#[prost(int32, tag = "7")]
pub audio_channel_count: i32,
/// This needs to be set to `true` explicitly and `audio_channel_count` > 1
/// to get each channel recognized separately. The recognition result will
/// contain a `channel_tag` field to state which channel that result belongs
/// to. If this is not true, we will only recognize the first channel. The
/// request is billed cumulatively for all channels recognized:
/// `audio_channel_count` multiplied by the length of the audio.
#[prost(bool, tag = "12")]
pub enable_separate_recognition_per_channel: bool,
/// Required. The language of the supplied audio as a
/// [BCP-47](<https://www.rfc-editor.org/rfc/bcp/bcp47.txt>) language tag.
/// Example: "en-US".
/// See [Language
/// Support](<https://cloud.google.com/speech-to-text/docs/languages>) for a list
/// of the currently supported language codes.
#[prost(string, tag = "3")]
pub language_code: ::prost::alloc::string::String,
/// A list of up to 3 additional
/// [BCP-47](<https://www.rfc-editor.org/rfc/bcp/bcp47.txt>) language tags,
/// listing possible alternative languages of the supplied audio.
/// See [Language
/// Support](<https://cloud.google.com/speech-to-text/docs/languages>) for a list
/// of the currently supported language codes. If alternative languages are
/// listed, recognition result will contain recognition in the most likely
/// language detected including the main language_code. The recognition result
/// will include the language tag of the language detected in the audio. Note:
/// This feature is only supported for Voice Command and Voice Search use cases
/// and performance may vary for other use cases (e.g., phone call
/// transcription).
#[prost(string, repeated, tag = "18")]
pub alternative_language_codes: ::prost::alloc::vec::Vec<
::prost::alloc::string::String,
>,
/// Maximum number of recognition hypotheses to be returned.
/// Specifically, the maximum number of `SpeechRecognitionAlternative` messages
/// within each `SpeechRecognitionResult`.
/// The server may return fewer than `max_alternatives`.
/// Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of
/// one. If omitted, will return a maximum of one.
#[prost(int32, tag = "4")]
pub max_alternatives: i32,
/// If set to `true`, the server will attempt to filter out
/// profanities, replacing all but the initial character in each filtered word
/// with asterisks, e.g. "f***". If set to `false` or omitted, profanities
/// won't be filtered out.
#[prost(bool, tag = "5")]
pub profanity_filter: bool,
/// Speech adaptation configuration improves the accuracy of speech
/// recognition. For more information, see the [speech
/// adaptation](<https://cloud.google.com/speech-to-text/docs/adaptation>)
/// documentation.
/// When speech adaptation is set it supersedes the `speech_contexts` field.
#[prost(message, optional, tag = "20")]
pub adaptation: ::core::option::Option<SpeechAdaptation>,
/// Optional. Use transcription normalization to automatically replace parts of
/// the transcript with phrases of your choosing. For StreamingRecognize, this
/// normalization only applies to stable partial transcripts (stability > 0.8)
/// and final transcripts.
#[prost(message, optional, tag = "24")]
pub transcript_normalization: ::core::option::Option<TranscriptNormalization>,
/// Array of [SpeechContext][google.cloud.speech.v1.SpeechContext].
/// A means to provide context to assist the speech recognition. For more
/// information, see
/// [speech
/// adaptation](<https://cloud.google.com/speech-to-text/docs/adaptation>).
#[prost(message, repeated, tag = "6")]
pub speech_contexts: ::prost::alloc::vec::Vec<SpeechContext>,
/// If `true`, the top result includes a list of words and
/// the start and end time offsets (timestamps) for those words. If
/// `false`, no word-level time offset information is returned. The default is
/// `false`.
#[prost(bool, tag = "8")]
pub enable_word_time_offsets: bool,
/// If `true`, the top result includes a list of words and the
/// confidence for those words. If `false`, no word-level confidence
/// information is returned. The default is `false`.
#[prost(bool, tag = "15")]
pub enable_word_confidence: bool,
/// If 'true', adds punctuation to recognition result hypotheses.
/// This feature is only available in select languages. Setting this for
/// requests in other languages has no effect at all.
/// The default 'false' value does not add punctuation to result hypotheses.
#[prost(bool, tag = "11")]
pub enable_automatic_punctuation: bool,
/// The spoken punctuation behavior for the call
/// If not set, uses default behavior based on model of choice
/// e.g. command_and_search will enable spoken punctuation by default
/// If 'true', replaces spoken punctuation with the corresponding symbols in
/// the request. For example, "how are you question mark" becomes "how are
/// you?". See <https://cloud.google.com/speech-to-text/docs/spoken-punctuation>
/// for support. If 'false', spoken punctuation is not replaced.
#[prost(message, optional, tag = "22")]
pub enable_spoken_punctuation: ::core::option::Option<bool>,
/// The spoken emoji behavior for the call
/// If not set, uses default behavior based on model of choice
/// If 'true', adds spoken emoji formatting for the request. This will replace
/// spoken emojis with the corresponding Unicode symbols in the final
/// transcript. If 'false', spoken emojis are not replaced.
#[prost(message, optional, tag = "23")]
pub enable_spoken_emojis: ::core::option::Option<bool>,
/// Config to enable speaker diarization and set additional
/// parameters to make diarization better suited for your application.
/// Note: When this is enabled, we send all the words from the beginning of the
/// audio for the top alternative in every consecutive STREAMING responses.
/// This is done in order to improve our speaker tags as our models learn to
/// identify the speakers in the conversation over time.
/// For non-streaming requests, the diarization results will be provided only
/// in the top alternative of the FINAL SpeechRecognitionResult.
#[prost(message, optional, tag = "19")]
pub diarization_config: ::core::option::Option<SpeakerDiarizationConfig>,
/// Metadata regarding this request.
#[prost(message, optional, tag = "9")]
pub metadata: ::core::option::Option<RecognitionMetadata>,
/// Which model to select for the given request. Select the model
/// best suited to your domain to get best results. If a model is not
/// explicitly specified, then we auto-select a model based on the parameters
/// in the RecognitionConfig.
/// <table>
/// <tr>
/// <td><b>Model</b></td>
/// <td><b>Description</b></td>
/// </tr>
/// <tr>
/// <td><code>latest_long</code></td>
/// <td>Best for long form content like media or conversation.</td>
/// </tr>
/// <tr>
/// <td><code>latest_short</code></td>
/// <td>Best for short form content like commands or single shot directed
/// speech.</td>
/// </tr>
/// <tr>
/// <td><code>command_and_search</code></td>
/// <td>Best for short queries such as voice commands or voice search.</td>
/// </tr>
/// <tr>
/// <td><code>phone_call</code></td>
/// <td>Best for audio that originated from a phone call (typically
/// recorded at an 8khz sampling rate).</td>
/// </tr>
/// <tr>
/// <td><code>video</code></td>
/// <td>Best for audio that originated from video or includes multiple
/// speakers. Ideally the audio is recorded at a 16khz or greater
/// sampling rate. This is a premium model that costs more than the
/// standard rate.</td>
/// </tr>
/// <tr>
/// <td><code>default</code></td>
/// <td>Best for audio that is not one of the specific audio models.
/// For example, long-form audio. Ideally the audio is high-fidelity,
/// recorded at a 16khz or greater sampling rate.</td>
/// </tr>
/// <tr>
/// <td><code>medical_conversation</code></td>
/// <td>Best for audio that originated from a conversation between a
/// medical provider and patient.</td>
/// </tr>
/// <tr>
/// <td><code>medical_dictation</code></td>
/// <td>Best for audio that originated from dictation notes by a medical
/// provider.</td>
/// </tr>
/// </table>
#[prost(string, tag = "13")]
pub model: ::prost::alloc::string::String,
/// Set to true to use an enhanced model for speech recognition.
/// If `use_enhanced` is set to true and the `model` field is not set, then
/// an appropriate enhanced model is chosen if an enhanced model exists for
/// the audio.
///
/// If `use_enhanced` is true and an enhanced version of the specified model
/// does not exist, then the speech is recognized using the standard version
/// of the specified model.
#[prost(bool, tag = "14")]
pub use_enhanced: bool,
}
/// Nested message and enum types in `RecognitionConfig`.
pub mod recognition_config {
/// The encoding of the audio data sent in the request.
///
/// All encodings support only 1 channel (mono) audio, unless the
/// `audio_channel_count` and `enable_separate_recognition_per_channel` fields
/// are set.
///
/// For best results, the audio source should be captured and transmitted using
/// a lossless encoding (`FLAC` or `LINEAR16`). The accuracy of the speech
/// recognition can be reduced if lossy codecs are used to capture or transmit
/// audio, particularly if background noise is present. Lossy codecs include
/// `MULAW`, `AMR`, `AMR_WB`, `OGG_OPUS`, `SPEEX_WITH_HEADER_BYTE`, `MP3`,
/// and `WEBM_OPUS`.
///
/// The `FLAC` and `WAV` audio file formats include a header that describes the
/// included audio content. You can request recognition for `WAV` files that
/// contain either `LINEAR16` or `MULAW` encoded audio.
/// If you send `FLAC` or `WAV` audio file format in
/// your request, you do not need to specify an `AudioEncoding`; the audio
/// encoding format is determined from the file header. If you specify
/// an `AudioEncoding` when you send send `FLAC` or `WAV` audio, the
/// encoding configuration must match the encoding described in the audio
/// header; otherwise the request returns an
/// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
/// code.
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum AudioEncoding {
/// Not specified.
EncodingUnspecified = 0,
/// Uncompressed 16-bit signed little-endian samples (Linear PCM).
Linear16 = 1,
/// `FLAC` (Free Lossless Audio
/// Codec) is the recommended encoding because it is
/// lossless--therefore recognition is not compromised--and
/// requires only about half the bandwidth of `LINEAR16`. `FLAC` stream
/// encoding supports 16-bit and 24-bit samples, however, not all fields in
/// `STREAMINFO` are supported.
Flac = 2,
/// 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
Mulaw = 3,
/// Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
Amr = 4,
/// Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
AmrWb = 5,
/// Opus encoded audio frames in Ogg container
/// ([OggOpus](<https://wiki.xiph.org/OggOpus>)).
/// `sample_rate_hertz` must be one of 8000, 12000, 16000, 24000, or 48000.
OggOpus = 6,
/// Although the use of lossy encodings is not recommended, if a very low
/// bitrate encoding is required, `OGG_OPUS` is highly preferred over
/// Speex encoding. The [Speex](<https://speex.org/>) encoding supported by
/// Cloud Speech API has a header byte in each block, as in MIME type
/// `audio/x-speex-with-header-byte`.
/// It is a variant of the RTP Speex encoding defined in
/// [RFC 5574](<https://tools.ietf.org/html/rfc5574>).
/// The stream is a sequence of blocks, one block per RTP packet. Each block
/// starts with a byte containing the length of the block, in bytes, followed
/// by one or more frames of Speex data, padded to an integral number of
/// bytes (octets) as specified in RFC 5574. In other words, each RTP header
/// is replaced with a single byte containing the block length. Only Speex
/// wideband is supported. `sample_rate_hertz` must be 16000.
SpeexWithHeaderByte = 7,
/// MP3 audio. MP3 encoding is a Beta feature and only available in
/// v1p1beta1. Support all standard MP3 bitrates (which range from 32-320
/// kbps). When using this encoding, `sample_rate_hertz` has to match the
/// sample rate of the file being used.
Mp3 = 8,
/// Opus encoded audio frames in WebM container
/// ([OggOpus](<https://wiki.xiph.org/OggOpus>)). `sample_rate_hertz` must be
/// one of 8000, 12000, 16000, 24000, or 48000.
WebmOpus = 9,
}
impl AudioEncoding {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
AudioEncoding::EncodingUnspecified => "ENCODING_UNSPECIFIED",
AudioEncoding::Linear16 => "LINEAR16",
AudioEncoding::Flac => "FLAC",
AudioEncoding::Mulaw => "MULAW",
AudioEncoding::Amr => "AMR",
AudioEncoding::AmrWb => "AMR_WB",
AudioEncoding::OggOpus => "OGG_OPUS",
AudioEncoding::SpeexWithHeaderByte => "SPEEX_WITH_HEADER_BYTE",
AudioEncoding::Mp3 => "MP3",
AudioEncoding::WebmOpus => "WEBM_OPUS",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"ENCODING_UNSPECIFIED" => Some(Self::EncodingUnspecified),
"LINEAR16" => Some(Self::Linear16),
"FLAC" => Some(Self::Flac),
"MULAW" => Some(Self::Mulaw),
"AMR" => Some(Self::Amr),
"AMR_WB" => Some(Self::AmrWb),
"OGG_OPUS" => Some(Self::OggOpus),
"SPEEX_WITH_HEADER_BYTE" => Some(Self::SpeexWithHeaderByte),
"MP3" => Some(Self::Mp3),
"WEBM_OPUS" => Some(Self::WebmOpus),
_ => None,
}
}
}
}
/// Config to enable speaker diarization.
#[derive(Clone, Copy, PartialEq, ::prost::Message)]
pub struct SpeakerDiarizationConfig {
/// If 'true', enables speaker detection for each recognized word in
/// the top alternative of the recognition result using a speaker_label
/// provided in the WordInfo.
#[prost(bool, tag = "1")]
pub enable_speaker_diarization: bool,
/// Minimum number of speakers in the conversation. This range gives you more
/// flexibility by allowing the system to automatically determine the correct
/// number of speakers. If not set, the default value is 2.
#[prost(int32, tag = "2")]
pub min_speaker_count: i32,
/// Maximum number of speakers in the conversation. This range gives you more
/// flexibility by allowing the system to automatically determine the correct
/// number of speakers. If not set, the default value is 6.
#[prost(int32, tag = "3")]
pub max_speaker_count: i32,
/// Output only. Unused.
#[deprecated]
#[prost(int32, tag = "5")]
pub speaker_tag: i32,
}
/// Description of audio data to be recognized.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RecognitionMetadata {
/// The use case most closely describing the audio content to be recognized.
#[prost(enumeration = "recognition_metadata::InteractionType", tag = "1")]
pub interaction_type: i32,
/// The industry vertical to which this speech recognition request most
/// closely applies. This is most indicative of the topics contained
/// in the audio. Use the 6-digit NAICS code to identify the industry
/// vertical - see <https://www.naics.com/search/.>
#[prost(uint32, tag = "3")]
pub industry_naics_code_of_audio: u32,
/// The audio type that most closely describes the audio being recognized.
#[prost(enumeration = "recognition_metadata::MicrophoneDistance", tag = "4")]
pub microphone_distance: i32,
/// The original media the speech was recorded on.
#[prost(enumeration = "recognition_metadata::OriginalMediaType", tag = "5")]
pub original_media_type: i32,
/// The type of device the speech was recorded with.
#[prost(enumeration = "recognition_metadata::RecordingDeviceType", tag = "6")]
pub recording_device_type: i32,
/// The device used to make the recording. Examples 'Nexus 5X' or
/// 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
/// 'Cardioid Microphone'.
#[prost(string, tag = "7")]
pub recording_device_name: ::prost::alloc::string::String,
/// Mime type of the original audio file. For example `audio/m4a`,
/// `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`.
/// A list of possible audio mime types is maintained at
/// <http://www.iana.org/assignments/media-types/media-types.xhtml#audio>
#[prost(string, tag = "8")]
pub original_mime_type: ::prost::alloc::string::String,
/// Description of the content. Eg. "Recordings of federal supreme court
/// hearings from 2012".
#[prost(string, tag = "10")]
pub audio_topic: ::prost::alloc::string::String,
}
/// Nested message and enum types in `RecognitionMetadata`.
pub mod recognition_metadata {
/// Use case categories that the audio recognition request can be described
/// by.
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum InteractionType {
/// Use case is either unknown or is something other than one of the other
/// values below.
Unspecified = 0,
/// Multiple people in a conversation or discussion. For example in a
/// meeting with two or more people actively participating. Typically
/// all the primary people speaking would be in the same room (if not,
/// see PHONE_CALL)
Discussion = 1,
/// One or more persons lecturing or presenting to others, mostly
/// uninterrupted.
Presentation = 2,
/// A phone-call or video-conference in which two or more people, who are
/// not in the same room, are actively participating.
PhoneCall = 3,
/// A recorded message intended for another person to listen to.
Voicemail = 4,
/// Professionally produced audio (eg. TV Show, Podcast).
ProfessionallyProduced = 5,
/// Transcribe spoken questions and queries into text.
VoiceSearch = 6,
/// Transcribe voice commands, such as for controlling a device.
VoiceCommand = 7,
/// Transcribe speech to text to create a written document, such as a
/// text-message, email or report.
Dictation = 8,
}
impl InteractionType {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
InteractionType::Unspecified => "INTERACTION_TYPE_UNSPECIFIED",
InteractionType::Discussion => "DISCUSSION",
InteractionType::Presentation => "PRESENTATION",
InteractionType::PhoneCall => "PHONE_CALL",
InteractionType::Voicemail => "VOICEMAIL",
InteractionType::ProfessionallyProduced => "PROFESSIONALLY_PRODUCED",
InteractionType::VoiceSearch => "VOICE_SEARCH",
InteractionType::VoiceCommand => "VOICE_COMMAND",
InteractionType::Dictation => "DICTATION",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"INTERACTION_TYPE_UNSPECIFIED" => Some(Self::Unspecified),
"DISCUSSION" => Some(Self::Discussion),
"PRESENTATION" => Some(Self::Presentation),
"PHONE_CALL" => Some(Self::PhoneCall),
"VOICEMAIL" => Some(Self::Voicemail),
"PROFESSIONALLY_PRODUCED" => Some(Self::ProfessionallyProduced),
"VOICE_SEARCH" => Some(Self::VoiceSearch),
"VOICE_COMMAND" => Some(Self::VoiceCommand),
"DICTATION" => Some(Self::Dictation),
_ => None,
}
}
}
/// Enumerates the types of capture settings describing an audio file.
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum MicrophoneDistance {
/// Audio type is not known.
Unspecified = 0,
/// The audio was captured from a closely placed microphone. Eg. phone,
/// dictaphone, or handheld microphone. Generally if there speaker is within
/// 1 meter of the microphone.
Nearfield = 1,
/// The speaker if within 3 meters of the microphone.
Midfield = 2,
/// The speaker is more than 3 meters away from the microphone.
Farfield = 3,
}
impl MicrophoneDistance {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
MicrophoneDistance::Unspecified => "MICROPHONE_DISTANCE_UNSPECIFIED",
MicrophoneDistance::Nearfield => "NEARFIELD",
MicrophoneDistance::Midfield => "MIDFIELD",
MicrophoneDistance::Farfield => "FARFIELD",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"MICROPHONE_DISTANCE_UNSPECIFIED" => Some(Self::Unspecified),
"NEARFIELD" => Some(Self::Nearfield),
"MIDFIELD" => Some(Self::Midfield),
"FARFIELD" => Some(Self::Farfield),
_ => None,
}
}
}
/// The original media the speech was recorded on.
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum OriginalMediaType {
/// Unknown original media type.
Unspecified = 0,
/// The speech data is an audio recording.
Audio = 1,
/// The speech data originally recorded on a video.
Video = 2,
}
impl OriginalMediaType {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
OriginalMediaType::Unspecified => "ORIGINAL_MEDIA_TYPE_UNSPECIFIED",
OriginalMediaType::Audio => "AUDIO",
OriginalMediaType::Video => "VIDEO",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"ORIGINAL_MEDIA_TYPE_UNSPECIFIED" => Some(Self::Unspecified),
"AUDIO" => Some(Self::Audio),
"VIDEO" => Some(Self::Video),
_ => None,
}
}
}
/// The type of device the speech was recorded with.
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum RecordingDeviceType {
/// The recording device is unknown.
Unspecified = 0,
/// Speech was recorded on a smartphone.
Smartphone = 1,
/// Speech was recorded using a personal computer or tablet.
Pc = 2,
/// Speech was recorded over a phone line.
PhoneLine = 3,
/// Speech was recorded in a vehicle.
Vehicle = 4,
/// Speech was recorded outdoors.
OtherOutdoorDevice = 5,
/// Speech was recorded indoors.
OtherIndoorDevice = 6,
}
impl RecordingDeviceType {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
RecordingDeviceType::Unspecified => "RECORDING_DEVICE_TYPE_UNSPECIFIED",
RecordingDeviceType::Smartphone => "SMARTPHONE",
RecordingDeviceType::Pc => "PC",
RecordingDeviceType::PhoneLine => "PHONE_LINE",
RecordingDeviceType::Vehicle => "VEHICLE",
RecordingDeviceType::OtherOutdoorDevice => "OTHER_OUTDOOR_DEVICE",
RecordingDeviceType::OtherIndoorDevice => "OTHER_INDOOR_DEVICE",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"RECORDING_DEVICE_TYPE_UNSPECIFIED" => Some(Self::Unspecified),
"SMARTPHONE" => Some(Self::Smartphone),
"PC" => Some(Self::Pc),
"PHONE_LINE" => Some(Self::PhoneLine),
"VEHICLE" => Some(Self::Vehicle),
"OTHER_OUTDOOR_DEVICE" => Some(Self::OtherOutdoorDevice),
"OTHER_INDOOR_DEVICE" => Some(Self::OtherIndoorDevice),
_ => None,
}
}
}
}
/// Provides "hints" to the speech recognizer to favor specific words and phrases
/// in the results.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SpeechContext {
/// A list of strings containing words and phrases "hints" so that
/// the speech recognition is more likely to recognize them. This can be used
/// to improve the accuracy for specific words and phrases, for example, if
/// specific commands are typically spoken by the user. This can also be used
/// to add additional words to the vocabulary of the recognizer. See
/// [usage limits](<https://cloud.google.com/speech-to-text/quotas#content>).
///
/// List items can also be set to classes for groups of words that represent
/// common concepts that occur in natural language. For example, rather than
/// providing phrase hints for every month of the year, using the $MONTH class
/// improves the likelihood of correctly transcribing audio that includes
/// months.
#[prost(string, repeated, tag = "1")]
pub phrases: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
/// Hint Boost. Positive value will increase the probability that a specific
/// phrase will be recognized over other similar sounding phrases. The higher
/// the boost, the higher the chance of false positive recognition as well.
/// Negative boost values would correspond to anti-biasing. Anti-biasing is not
/// enabled, so negative boost will simply be ignored. Though `boost` can
/// accept a wide range of positive values, most use cases are best served with
/// values between 0 and 20. We recommend using a binary search approach to
/// finding the optimal value for your use case.
#[prost(float, tag = "4")]
pub boost: f32,
}
/// Contains audio data in the encoding specified in the `RecognitionConfig`.
/// Either `content` or `uri` must be supplied. Supplying both or neither
/// returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
/// See [content limits](<https://cloud.google.com/speech-to-text/quotas#content>).
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RecognitionAudio {
/// The audio source, which is either inline content or a Google Cloud
/// Storage uri.
#[prost(oneof = "recognition_audio::AudioSource", tags = "1, 2")]
pub audio_source: ::core::option::Option<recognition_audio::AudioSource>,
}
/// Nested message and enum types in `RecognitionAudio`.
pub mod recognition_audio {
/// The audio source, which is either inline content or a Google Cloud
/// Storage uri.
#[derive(Clone, PartialEq, ::prost::Oneof)]
pub enum AudioSource {
/// The audio data bytes encoded as specified in
/// `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a
/// pure binary representation, whereas JSON representations use base64.
#[prost(bytes, tag = "1")]
Content(::prost::bytes::Bytes),
/// URI that points to a file that contains audio data bytes as specified in
/// `RecognitionConfig`. The file must not be compressed (for example, gzip).
/// Currently, only Google Cloud Storage URIs are
/// supported, which must be specified in the following format:
/// `gs://bucket_name/object_name` (other URI formats return
/// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
/// For more information, see [Request
/// URIs](<https://cloud.google.com/storage/docs/reference-uris>).
#[prost(string, tag = "2")]
Uri(::prost::alloc::string::String),
}
}
/// The only message returned to the client by the `Recognize` method. It
/// contains the result as zero or more sequential `SpeechRecognitionResult`
/// messages.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct RecognizeResponse {
/// Sequential list of transcription results corresponding to
/// sequential portions of audio.
#[prost(message, repeated, tag = "2")]
pub results: ::prost::alloc::vec::Vec<SpeechRecognitionResult>,
/// When available, billed audio seconds for the corresponding request.
#[prost(message, optional, tag = "3")]
pub total_billed_time: ::core::option::Option<::prost_types::Duration>,
/// Provides information on adaptation behavior in response
#[prost(message, optional, tag = "7")]
pub speech_adaptation_info: ::core::option::Option<SpeechAdaptationInfo>,
/// The ID associated with the request. This is a unique ID specific only to
/// the given request.
#[prost(int64, tag = "8")]
pub request_id: i64,
}
/// The only message returned to the client by the `LongRunningRecognize` method.
/// It contains the result as zero or more sequential `SpeechRecognitionResult`
/// messages. It is included in the `result.response` field of the `Operation`
/// returned by the `GetOperation` call of the `google::longrunning::Operations`
/// service.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct LongRunningRecognizeResponse {
/// Sequential list of transcription results corresponding to
/// sequential portions of audio.
#[prost(message, repeated, tag = "2")]
pub results: ::prost::alloc::vec::Vec<SpeechRecognitionResult>,
/// When available, billed audio seconds for the corresponding request.
#[prost(message, optional, tag = "3")]
pub total_billed_time: ::core::option::Option<::prost_types::Duration>,
/// Original output config if present in the request.
#[prost(message, optional, tag = "6")]
pub output_config: ::core::option::Option<TranscriptOutputConfig>,
/// If the transcript output fails this field contains the relevant error.
#[prost(message, optional, tag = "7")]
pub output_error: ::core::option::Option<super::super::super::rpc::Status>,
/// Provides information on speech adaptation behavior in response
#[prost(message, optional, tag = "8")]
pub speech_adaptation_info: ::core::option::Option<SpeechAdaptationInfo>,
/// The ID associated with the request. This is a unique ID specific only to
/// the given request.
#[prost(int64, tag = "9")]
pub request_id: i64,
}
/// Describes the progress of a long-running `LongRunningRecognize` call. It is
/// included in the `metadata` field of the `Operation` returned by the
/// `GetOperation` call of the `google::longrunning::Operations` service.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct LongRunningRecognizeMetadata {
/// Approximate percentage of audio processed thus far. Guaranteed to be 100
/// when the audio is fully processed and the results are available.
#[prost(int32, tag = "1")]
pub progress_percent: i32,
/// Time when the request was received.
#[prost(message, optional, tag = "2")]
pub start_time: ::core::option::Option<::prost_types::Timestamp>,
/// Time of the most recent processing update.
#[prost(message, optional, tag = "3")]
pub last_update_time: ::core::option::Option<::prost_types::Timestamp>,
/// Output only. The URI of the audio file being transcribed. Empty if the
/// audio was sent as byte content.
#[prost(string, tag = "4")]
pub uri: ::prost::alloc::string::String,
}
/// `StreamingRecognizeResponse` is the only message returned to the client by
/// `StreamingRecognize`. A series of zero or more `StreamingRecognizeResponse`
/// messages are streamed back to the client. If there is no recognizable
/// audio, and `single_utterance` is set to false, then no messages are streamed
/// back to the client.
///
/// Here's an example of a series of `StreamingRecognizeResponse`s that might be
/// returned while processing audio:
///
/// 1. results { alternatives { transcript: "tube" } stability: 0.01 }
///
/// 2. results { alternatives { transcript: "to be a" } stability: 0.01 }
///
/// 3. results { alternatives { transcript: "to be" } stability: 0.9 }
/// results { alternatives { transcript: " or not to be" } stability: 0.01 }
///
/// 4. results { alternatives { transcript: "to be or not to be"
/// confidence: 0.92 }
/// alternatives { transcript: "to bee or not to bee" }
/// is_final: true }
///
/// 5. results { alternatives { transcript: " that's" } stability: 0.01 }
///
/// 6. results { alternatives { transcript: " that is" } stability: 0.9 }
/// results { alternatives { transcript: " the question" } stability: 0.01 }
///
/// 7. results { alternatives { transcript: " that is the question"
/// confidence: 0.98 }
/// alternatives { transcript: " that was the question" }
/// is_final: true }
///
/// Notes:
///
/// - Only two of the above responses #4 and #7 contain final results; they are
/// indicated by `is_final: true`. Concatenating these together generates the
/// full transcript: "to be or not to be that is the question".
///
/// - The others contain interim `results`. #3 and #6 contain two interim
/// `results`: the first portion has a high stability and is less likely to
/// change; the second portion has a low stability and is very likely to
/// change. A UI designer might choose to show only high stability `results`.
///
/// - The specific `stability` and `confidence` values shown above are only for
/// illustrative purposes. Actual values may vary.
///
/// - In each response, only one of these fields will be set:
/// `error`,
/// `speech_event_type`, or
/// one or more (repeated) `results`.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct StreamingRecognizeResponse {
/// If set, returns a [google.rpc.Status][google.rpc.Status] message that
/// specifies the error for the operation.
#[prost(message, optional, tag = "1")]
pub error: ::core::option::Option<super::super::super::rpc::Status>,
/// This repeated list contains zero or more results that
/// correspond to consecutive portions of the audio currently being processed.
/// It contains zero or one `is_final=true` result (the newly settled portion),
/// followed by zero or more `is_final=false` results (the interim results).
#[prost(message, repeated, tag = "2")]
pub results: ::prost::alloc::vec::Vec<StreamingRecognitionResult>,
/// Indicates the type of speech event.
#[prost(enumeration = "streaming_recognize_response::SpeechEventType", tag = "4")]
pub speech_event_type: i32,
/// Time offset between the beginning of the audio and event emission.
#[prost(message, optional, tag = "8")]
pub speech_event_time: ::core::option::Option<::prost_types::Duration>,
/// When available, billed audio seconds for the stream.
/// Set only if this is the last response in the stream.
#[prost(message, optional, tag = "5")]
pub total_billed_time: ::core::option::Option<::prost_types::Duration>,
/// Provides information on adaptation behavior in response
#[prost(message, optional, tag = "9")]
pub speech_adaptation_info: ::core::option::Option<SpeechAdaptationInfo>,
/// The ID associated with the request. This is a unique ID specific only to
/// the given request.
#[prost(int64, tag = "10")]
pub request_id: i64,
}
/// Nested message and enum types in `StreamingRecognizeResponse`.
pub mod streaming_recognize_response {
/// Indicates the type of speech event.
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum SpeechEventType {
/// No speech event specified.
SpeechEventUnspecified = 0,
/// This event indicates that the server has detected the end of the user's
/// speech utterance and expects no additional speech. Therefore, the server
/// will not process additional audio (although it may subsequently return
/// additional results). The client should stop sending additional audio
/// data, half-close the gRPC connection, and wait for any additional results
/// until the server closes the gRPC connection. This event is only sent if
/// `single_utterance` was set to `true`, and is not used otherwise.
EndOfSingleUtterance = 1,
/// This event indicates that the server has detected the beginning of human
/// voice activity in the stream. This event can be returned multiple times
/// if speech starts and stops repeatedly throughout the stream. This event
/// is only sent if `voice_activity_events` is set to true.
SpeechActivityBegin = 2,
/// This event indicates that the server has detected the end of human voice
/// activity in the stream. This event can be returned multiple times if
/// speech starts and stops repeatedly throughout the stream. This event is
/// only sent if `voice_activity_events` is set to true.
SpeechActivityEnd = 3,
/// This event indicates that the user-set timeout for speech activity begin
/// or end has exceeded. Upon receiving this event, the client is expected to
/// send a half close. Further audio will not be processed.
SpeechActivityTimeout = 4,
}
impl SpeechEventType {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
SpeechEventType::SpeechEventUnspecified => "SPEECH_EVENT_UNSPECIFIED",
SpeechEventType::EndOfSingleUtterance => "END_OF_SINGLE_UTTERANCE",
SpeechEventType::SpeechActivityBegin => "SPEECH_ACTIVITY_BEGIN",
SpeechEventType::SpeechActivityEnd => "SPEECH_ACTIVITY_END",
SpeechEventType::SpeechActivityTimeout => "SPEECH_ACTIVITY_TIMEOUT",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"SPEECH_EVENT_UNSPECIFIED" => Some(Self::SpeechEventUnspecified),
"END_OF_SINGLE_UTTERANCE" => Some(Self::EndOfSingleUtterance),
"SPEECH_ACTIVITY_BEGIN" => Some(Self::SpeechActivityBegin),
"SPEECH_ACTIVITY_END" => Some(Self::SpeechActivityEnd),
"SPEECH_ACTIVITY_TIMEOUT" => Some(Self::SpeechActivityTimeout),
_ => None,
}
}
}
}
/// A streaming speech recognition result corresponding to a portion of the audio
/// that is currently being processed.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct StreamingRecognitionResult {
/// May contain one or more recognition hypotheses (up to the
/// maximum specified in `max_alternatives`).
/// These alternatives are ordered in terms of accuracy, with the top (first)
/// alternative being the most probable, as ranked by the recognizer.
#[prost(message, repeated, tag = "1")]
pub alternatives: ::prost::alloc::vec::Vec<SpeechRecognitionAlternative>,
/// If `false`, this `StreamingRecognitionResult` represents an
/// interim result that may change. If `true`, this is the final time the
/// speech service will return this particular `StreamingRecognitionResult`,
/// the recognizer will not return any further hypotheses for this portion of
/// the transcript and corresponding audio.
#[prost(bool, tag = "2")]
pub is_final: bool,
/// An estimate of the likelihood that the recognizer will not
/// change its guess about this interim result. Values range from 0.0
/// (completely unstable) to 1.0 (completely stable).
/// This field is only provided for interim results (`is_final=false`).
/// The default of 0.0 is a sentinel value indicating `stability` was not set.
#[prost(float, tag = "3")]
pub stability: f32,
/// Time offset of the end of this result relative to the
/// beginning of the audio.
#[prost(message, optional, tag = "4")]
pub result_end_time: ::core::option::Option<::prost_types::Duration>,
/// For multi-channel audio, this is the channel number corresponding to the
/// recognized result for the audio from that channel.
/// For audio_channel_count = N, its output values can range from '1' to 'N'.
#[prost(int32, tag = "5")]
pub channel_tag: i32,
/// Output only. The [BCP-47](<https://www.rfc-editor.org/rfc/bcp/bcp47.txt>)
/// language tag of the language in this result. This language code was
/// detected to have the most likelihood of being spoken in the audio.
#[prost(string, tag = "6")]
pub language_code: ::prost::alloc::string::String,
}
/// A speech recognition result corresponding to a portion of the audio.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SpeechRecognitionResult {
/// May contain one or more recognition hypotheses (up to the
/// maximum specified in `max_alternatives`).
/// These alternatives are ordered in terms of accuracy, with the top (first)
/// alternative being the most probable, as ranked by the recognizer.
#[prost(message, repeated, tag = "1")]
pub alternatives: ::prost::alloc::vec::Vec<SpeechRecognitionAlternative>,
/// For multi-channel audio, this is the channel number corresponding to the
/// recognized result for the audio from that channel.
/// For audio_channel_count = N, its output values can range from '1' to 'N'.
#[prost(int32, tag = "2")]
pub channel_tag: i32,
/// Time offset of the end of this result relative to the
/// beginning of the audio.
#[prost(message, optional, tag = "4")]
pub result_end_time: ::core::option::Option<::prost_types::Duration>,
/// Output only. The [BCP-47](<https://www.rfc-editor.org/rfc/bcp/bcp47.txt>)
/// language tag of the language in this result. This language code was
/// detected to have the most likelihood of being spoken in the audio.
#[prost(string, tag = "5")]
pub language_code: ::prost::alloc::string::String,
}
/// Alternative hypotheses (a.k.a. n-best list).
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SpeechRecognitionAlternative {
/// Transcript text representing the words that the user spoke.
/// In languages that use spaces to separate words, the transcript might have a
/// leading space if it isn't the first result. You can concatenate each result
/// to obtain the full transcript without using a separator.
#[prost(string, tag = "1")]
pub transcript: ::prost::alloc::string::String,
/// The confidence estimate between 0.0 and 1.0. A higher number
/// indicates an estimated greater likelihood that the recognized words are
/// correct. This field is set only for the top alternative of a non-streaming
/// result or, of a streaming result where `is_final=true`.
/// This field is not guaranteed to be accurate and users should not rely on it
/// to be always provided.
/// The default of 0.0 is a sentinel value indicating `confidence` was not set.
#[prost(float, tag = "2")]
pub confidence: f32,
/// A list of word-specific information for each recognized word.
/// Note: When `enable_speaker_diarization` is true, you will see all the words
/// from the beginning of the audio.
#[prost(message, repeated, tag = "3")]
pub words: ::prost::alloc::vec::Vec<WordInfo>,
}
/// Word-specific information for recognized words.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct WordInfo {
/// Time offset relative to the beginning of the audio,
/// and corresponding to the start of the spoken word.
/// This field is only set if `enable_word_time_offsets=true` and only
/// in the top hypothesis.
/// This is an experimental feature and the accuracy of the time offset can
/// vary.
#[prost(message, optional, tag = "1")]
pub start_time: ::core::option::Option<::prost_types::Duration>,
/// Time offset relative to the beginning of the audio,
/// and corresponding to the end of the spoken word.
/// This field is only set if `enable_word_time_offsets=true` and only
/// in the top hypothesis.
/// This is an experimental feature and the accuracy of the time offset can
/// vary.
#[prost(message, optional, tag = "2")]
pub end_time: ::core::option::Option<::prost_types::Duration>,
/// The word corresponding to this set of information.
#[prost(string, tag = "3")]
pub word: ::prost::alloc::string::String,
/// The confidence estimate between 0.0 and 1.0. A higher number
/// indicates an estimated greater likelihood that the recognized words are
/// correct. This field is set only for the top alternative of a non-streaming
/// result or, of a streaming result where `is_final=true`.
/// This field is not guaranteed to be accurate and users should not rely on it
/// to be always provided.
/// The default of 0.0 is a sentinel value indicating `confidence` was not set.
#[prost(float, tag = "4")]
pub confidence: f32,
/// Output only. A distinct integer value is assigned for every speaker within
/// the audio. This field specifies which one of those speakers was detected to
/// have spoken this word. Value ranges from '1' to diarization_speaker_count.
/// speaker_tag is set if enable_speaker_diarization = 'true' and only for the
/// top alternative.
/// Note: Use speaker_label instead.
#[deprecated]
#[prost(int32, tag = "5")]
pub speaker_tag: i32,
/// Output only. A label value assigned for every unique speaker within the
/// audio. This field specifies which speaker was detected to have spoken this
/// word. For some models, like medical_conversation this can be actual speaker
/// role, for example "patient" or "provider", but generally this would be a
/// number identifying a speaker. This field is only set if
/// enable_speaker_diarization = 'true' and only for the top alternative.
#[prost(string, tag = "6")]
pub speaker_label: ::prost::alloc::string::String,
}
/// Information on speech adaptation use in results
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct SpeechAdaptationInfo {
/// Whether there was a timeout when applying speech adaptation. If true,
/// adaptation had no effect in the response transcript.
#[prost(bool, tag = "1")]
pub adaptation_timeout: bool,
/// If set, returns a message specifying which part of the speech adaptation
/// request timed out.
#[prost(string, tag = "4")]
pub timeout_message: ::prost::alloc::string::String,
}
/// Generated client implementations.
pub mod speech_client {
#![allow(unused_variables, dead_code, missing_docs, clippy::let_unit_value)]
use tonic::codegen::*;
use tonic::codegen::http::Uri;
/// Service that implements Google Cloud Speech API.
#[derive(Debug, Clone)]
pub struct SpeechClient<T> {
inner: tonic::client::Grpc<T>,
}
impl<T> SpeechClient<T>
where
T: tonic::client::GrpcService<tonic::body::BoxBody>,
T::Error: Into<StdError>,
T::ResponseBody: Body<Data = Bytes> + std::marker::Send + 'static,
<T::ResponseBody as Body>::Error: Into<StdError> + std::marker::Send,
{
pub fn new(inner: T) -> Self {
let inner = tonic::client::Grpc::new(inner);
Self { inner }
}
pub fn with_origin(inner: T, origin: Uri) -> Self {
let inner = tonic::client::Grpc::with_origin(inner, origin);
Self { inner }
}
pub fn with_interceptor<F>(
inner: T,
interceptor: F,
) -> SpeechClient<InterceptedService<T, F>>
where
F: tonic::service::Interceptor,
T::ResponseBody: Default,
T: tonic::codegen::Service<
http::Request<tonic::body::BoxBody>,
Response = http::Response<
<T as tonic::client::GrpcService<tonic::body::BoxBody>>::ResponseBody,
>,
>,
<T as tonic::codegen::Service<
http::Request<tonic::body::BoxBody>,
>>::Error: Into<StdError> + std::marker::Send + std::marker::Sync,
{
SpeechClient::new(InterceptedService::new(inner, interceptor))
}
/// Compress requests with the given encoding.
///
/// This requires the server to support it otherwise it might respond with an
/// error.
#[must_use]
pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.send_compressed(encoding);
self
}
/// Enable decompressing responses.
#[must_use]
pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.accept_compressed(encoding);
self
}
/// Limits the maximum size of a decoded message.
///
/// Default: `4MB`
#[must_use]
pub fn max_decoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_decoding_message_size(limit);
self
}
/// Limits the maximum size of an encoded message.
///
/// Default: `usize::MAX`
#[must_use]
pub fn max_encoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_encoding_message_size(limit);
self
}
/// Performs synchronous speech recognition: receive results after all audio
/// has been sent and processed.
pub async fn recognize(
&mut self,
request: impl tonic::IntoRequest<super::RecognizeRequest>,
) -> std::result::Result<
tonic::Response<super::RecognizeResponse>,
tonic::Status,
> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Speech/Recognize",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(GrpcMethod::new("google.cloud.speech.v1.Speech", "Recognize"));
self.inner.unary(req, path, codec).await
}
/// Performs asynchronous speech recognition: receive results via the
/// google.longrunning.Operations interface. Returns either an
/// `Operation.error` or an `Operation.response` which contains
/// a `LongRunningRecognizeResponse` message.
/// For more information on asynchronous speech recognition, see the
/// [how-to](https://cloud.google.com/speech-to-text/docs/async-recognize).
pub async fn long_running_recognize(
&mut self,
request: impl tonic::IntoRequest<super::LongRunningRecognizeRequest>,
) -> std::result::Result<
tonic::Response<super::super::super::super::longrunning::Operation>,
tonic::Status,
> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Speech/LongRunningRecognize",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Speech",
"LongRunningRecognize",
),
);
self.inner.unary(req, path, codec).await
}
/// Performs bidirectional streaming speech recognition: receive results while
/// sending audio. This method is only available via the gRPC API (not REST).
pub async fn streaming_recognize(
&mut self,
request: impl tonic::IntoStreamingRequest<
Message = super::StreamingRecognizeRequest,
>,
) -> std::result::Result<
tonic::Response<tonic::codec::Streaming<super::StreamingRecognizeResponse>>,
tonic::Status,
> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.speech.v1.Speech/StreamingRecognize",
);
let mut req = request.into_streaming_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.speech.v1.Speech",
"StreamingRecognize",
),
);
self.inner.streaming(req, path, codec).await
}
}
}