1
1
/*
2
- * (C) Copyright IBM Corp. 2018, 2024.
2
+ * (C) Copyright IBM Corp. 2024.
3
3
*
4
4
* Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
5
5
* the License. You may obtain a copy of the License at
@@ -51,6 +51,8 @@ public interface Model {
51
51
String DE_DE_NARROWBANDMODEL = "de-DE_NarrowbandModel" ;
52
52
/** de-DE_Telephony. */
53
53
String DE_DE_TELEPHONY = "de-DE_Telephony" ;
54
+ /** en-AU. */
55
+ String EN_AU = "en-AU" ;
54
56
/** en-AU_BroadbandModel. */
55
57
String EN_AU_BROADBANDMODEL = "en-AU_BroadbandModel" ;
56
58
/** en-AU_Multimedia. */
@@ -59,8 +61,12 @@ public interface Model {
59
61
String EN_AU_NARROWBANDMODEL = "en-AU_NarrowbandModel" ;
60
62
/** en-AU_Telephony. */
61
63
String EN_AU_TELEPHONY = "en-AU_Telephony" ;
64
+ /** en-IN. */
65
+ String EN_IN = "en-IN" ;
62
66
/** en-IN_Telephony. */
63
67
String EN_IN_TELEPHONY = "en-IN_Telephony" ;
68
+ /** en-GB. */
69
+ String EN_GB = "en-GB" ;
64
70
/** en-GB_BroadbandModel. */
65
71
String EN_GB_BROADBANDMODEL = "en-GB_BroadbandModel" ;
66
72
/** en-GB_Multimedia. */
@@ -69,6 +75,8 @@ public interface Model {
69
75
String EN_GB_NARROWBANDMODEL = "en-GB_NarrowbandModel" ;
70
76
/** en-GB_Telephony. */
71
77
String EN_GB_TELEPHONY = "en-GB_Telephony" ;
78
+ /** en-US. */
79
+ String EN_US = "en-US" ;
72
80
/** en-US_BroadbandModel. */
73
81
String EN_US_BROADBANDMODEL = "en-US_BroadbandModel" ;
74
82
/** en-US_Multimedia. */
@@ -111,6 +119,8 @@ public interface Model {
111
119
String ES_PE_BROADBANDMODEL = "es-PE_BroadbandModel" ;
112
120
/** es-PE_NarrowbandModel. */
113
121
String ES_PE_NARROWBANDMODEL = "es-PE_NarrowbandModel" ;
122
+ /** fr-CA. */
123
+ String FR_CA = "fr-CA" ;
114
124
/** fr-CA_BroadbandModel. */
115
125
String FR_CA_BROADBANDMODEL = "fr-CA_BroadbandModel" ;
116
126
/** fr-CA_Multimedia. */
@@ -119,6 +129,8 @@ public interface Model {
119
129
String FR_CA_NARROWBANDMODEL = "fr-CA_NarrowbandModel" ;
120
130
/** fr-CA_Telephony. */
121
131
String FR_CA_TELEPHONY = "fr-CA_Telephony" ;
132
+ /** fr-FR. */
133
+ String FR_FR = "fr-FR" ;
122
134
/** fr-FR_BroadbandModel. */
123
135
String FR_FR_BROADBANDMODEL = "fr-FR_BroadbandModel" ;
124
136
/** fr-FR_Multimedia. */
@@ -137,6 +149,8 @@ public interface Model {
137
149
String IT_IT_MULTIMEDIA = "it-IT_Multimedia" ;
138
150
/** it-IT_Telephony. */
139
151
String IT_IT_TELEPHONY = "it-IT_Telephony" ;
152
+ /** ja-JP. */
153
+ String JA_JP = "ja-JP" ;
140
154
/** ja-JP_BroadbandModel. */
141
155
String JA_JP_BROADBANDMODEL = "ja-JP_BroadbandModel" ;
142
156
/** ja-JP_Multimedia. */
@@ -952,9 +966,9 @@ public String baseModelVersion() {
952
966
* custom language model compared to those from the base model for the current request.
953
967
*
954
968
* <p>Specify a value between 0.0 and 1.0. Unless a different customization weight was specified
955
- * for the custom model when the model was trained, the default value is: * 0.3 for
956
- * previous-generation models * 0.2 for most next-generation models * 0.1 for next-generation
957
- * English and Japanese models
969
+ * for the custom model when the model was trained, the default value is: * 0.5 for large speech
970
+ * models * 0.3 for previous-generation models * 0.2 for most next-generation models * 0.1 for
971
+ * next-generation English and Japanese models
958
972
*
959
973
* <p>A customization weight that you specify overrides a weight that was specified when the
960
974
* custom model was trained. The default value yields the best performance in general. Assign a
@@ -1117,8 +1131,8 @@ public Boolean smartFormatting() {
1117
1131
/**
1118
1132
* Gets the smartFormattingVersion.
1119
1133
*
1120
- * <p>Smart formatting version is for next-generation models and that is supported in US English,
1121
- * Brazilian Portuguese, French and German languages.
1134
+ * <p>Smart formatting version for large speech models and next-generation models is supported in
1135
+ * US English, Brazilian Portuguese, French, German, Spanish and French Canadian languages.
1122
1136
*
1123
1137
* @return the smartFormattingVersion
1124
1138
*/
@@ -1135,8 +1149,8 @@ public Long smartFormattingVersion() {
1135
1149
* of whether you specify `false` for the parameter. * _For previous-generation models,_ the
1136
1150
* parameter can be used with Australian English, US English, German, Japanese, Korean, and
1137
1151
* Spanish (both broadband and narrowband models) and UK English (narrowband model) transcription
1138
- * only. * _For next-generation models,_ the parameter can be used with Czech, English
1139
- * (Australian, Indian, UK, and US), German, Japanese, Korean, and Spanish transcription only .
1152
+ * only. * _For large speech models and next-generation models,_ the parameter can be used with
1153
+ * all available languages .
1140
1154
*
1141
1155
* <p>See [Speaker
1142
1156
* labels](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-speaker-labels).
@@ -1310,8 +1324,8 @@ public Boolean splitTranscriptAtPhraseEnd() {
1310
1324
* <p>The values increase on a monotonic curve. Specifying one or two decimal places of precision
1311
1325
* (for example, `0.55`) is typically more than sufficient.
1312
1326
*
1313
- * <p>The parameter is supported with all next-generation models and with most previous-generation
1314
- * models. See [Speech detector
1327
+ * <p>The parameter is supported with all large speech models, next-generation models and with
1328
+ * most previous-generation models. See [Speech detector
1315
1329
* sensitivity](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-detection#detection-parameters-sensitivity)
1316
1330
* and [Language model
1317
1331
* support](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-detection#detection-support).
@@ -1336,8 +1350,8 @@ public Float speechDetectorSensitivity() {
1336
1350
* <p>The values increase on a monotonic curve. Specifying one or two decimal places of precision
1337
1351
* (for example, `0.55`) is typically more than sufficient.
1338
1352
*
1339
- * <p>The parameter is supported with all next-generation models and with most previous-generation
1340
- * models. See [Background audio
1353
+ * <p>The parameter is supported with all large speech models, next-generation models and with
1354
+ * most previous-generation models. See [Background audio
1341
1355
* suppression](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-detection#detection-parameters-suppression)
1342
1356
* and [Language model
1343
1357
* support](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-detection#detection-support).
@@ -1357,9 +1371,9 @@ public Float backgroundAudioSuppression() {
1357
1371
* parameter causes the models to produce results even more quickly, though the results might be
1358
1372
* less accurate when the parameter is used.
1359
1373
*
1360
- * <p>The parameter is not available for previous-generation `Broadband` and `Narrowband` models.
1361
- * It is available for most next-generation models. * For a list of next-generation models that
1362
- * support low latency, see [Supported next-generation language
1374
+ * <p>The parameter is not available for large speech models and previous-generation `Broadband`
1375
+ * and `Narrowband` models. It is available for most next-generation models. * For a list of
1376
+ * next-generation models that support low latency, see [Supported next-generation language
1363
1377
* models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-models-ng#models-ng-supported).
1364
1378
* * For more information about the `low_latency` parameter, see [Low
1365
1379
* latency](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-interim#low-latency).
@@ -1373,9 +1387,10 @@ public Boolean lowLatency() {
1373
1387
/**
1374
1388
* Gets the characterInsertionBias.
1375
1389
*
1376
- * <p>For next-generation models, an indication of whether the service is biased to recognize
1377
- * shorter or longer strings of characters when developing transcription hypotheses. By default,
1378
- * the service is optimized to produce the best balance of strings of different lengths.
1390
+ * <p>For large speech models and next-generation models, an indication of whether the service is
1391
+ * biased to recognize shorter or longer strings of characters when developing transcription
1392
+ * hypotheses. By default, the service is optimized to produce the best balance of strings of
1393
+ * different lengths.
1379
1394
*
1380
1395
* <p>The default bias is 0.0. The allowable range of values is -1.0 to 1.0. * Negative values
1381
1396
* bias the service to favor hypotheses with shorter strings of characters. * Positive values bias
0 commit comments