google-cloud-speech-v1 0.14.0 → 0.15.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (7) hide show
  1. checksums.yaml +4 -4
  2. data/lib/google/cloud/speech/v1/cloud_speech_pb.rb +1 -1
  3. data/lib/google/cloud/speech/v1/resource_pb.rb +3 -1
  4. data/lib/google/cloud/speech/v1/version.rb +1 -1
  5. data/proto_docs/google/cloud/speech/v1/cloud_speech.rb +24 -3
  6. data/proto_docs/google/cloud/speech/v1/resource.rb +30 -0
  7. metadata +2 -2
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: bd40d7af85f867e1d840a9e2a67b2c346804f07d3e85df56263ee47b3a4ff2fc
4
- data.tar.gz: 3bb1f7bb330cbe248765239febb1dc9e5eb81689dc438052a78686215e2f029f
3
+ metadata.gz: 06fbd18f76c6bb1319e13c2acedfd38bce39d84ea4100ee0a6b81ca8334713e0
4
+ data.tar.gz: 5a192f601581e3b12408fe82706d7baa349b74b13f1ecd4c90eb44e04c35bddb
5
5
  SHA512:
6
- metadata.gz: 1cbd0d8d40f9cbe64a5674f142500e4528c1b26c421095ebf13a9f71a059d1e6a973e88f50203bfc0cbe9a290721d51f753a71c52d050f32d0a62ebb78785ade
7
- data.tar.gz: f41d71cd3ff15922ff1caba43e26a2c5134410228cfadd9a828fadb4cfc8b94e99e48b8fe227b39284c7469e83f457cd104707f20ee8113af26133ddc4365b24
6
+ metadata.gz: de18f2eb452d6201357dc4ef5f55b060a793b5b60ee3da384def0ad6c8a442b2ac219f7bb7d8c0740bf37a6624ac902e170f66ffc429d67dcf35a425ae694a11
7
+ data.tar.gz: 3050660ec37ce8577dacbdea96a8a722b671128802c8ca92634bc11e1fb8e350d6ae74ba0a1ba1b90968623d67f9bf6783c699d832bcfaba6835a1471baa13b6
data/lib/google/cloud/speech/v1/cloud_speech_pb.rb CHANGED
@@ -15,7 +15,7 @@ require 'google/protobuf/wrappers_pb'
15
15
  require 'google/rpc/status_pb'
16
16
 
17
17
 
18
- descriptor_data = "\n)google/cloud/speech/v1/cloud_speech.proto\x12\x16google.cloud.speech.v1\x1a\x1cgoogle/api/annotations.proto\x1a\x17google/api/client.proto\x1a\x1fgoogle/api/field_behavior.proto\x1a%google/cloud/speech/v1/resource.proto\x1a#google/longrunning/operations.proto\x1a\x1egoogle/protobuf/duration.proto\x1a\x1fgoogle/protobuf/timestamp.proto\x1a\x1egoogle/protobuf/wrappers.proto\x1a\x17google/rpc/status.proto\"\x90\x01\n\x10RecognizeRequest\x12>\n\x06\x63onfig\x18\x01 \x01(\x0b\x32).google.cloud.speech.v1.RecognitionConfigB\x03\xe0\x41\x02\x12<\n\x05\x61udio\x18\x02 \x01(\x0b\x32(.google.cloud.speech.v1.RecognitionAudioB\x03\xe0\x41\x02\"\xe7\x01\n\x1bLongRunningRecognizeRequest\x12>\n\x06\x63onfig\x18\x01 \x01(\x0b\x32).google.cloud.speech.v1.RecognitionConfigB\x03\xe0\x41\x02\x12<\n\x05\x61udio\x18\x02 \x01(\x0b\x32(.google.cloud.speech.v1.RecognitionAudioB\x03\xe0\x41\x02\x12J\n\routput_config\x18\x04 \x01(\x0b\x32..google.cloud.speech.v1.TranscriptOutputConfigB\x03\xe0\x41\x01\":\n\x16TranscriptOutputConfig\x12\x11\n\x07gcs_uri\x18\x01 \x01(\tH\x00\x42\r\n\x0boutput_type\"\x99\x01\n\x19StreamingRecognizeRequest\x12N\n\x10streaming_config\x18\x01 \x01(\x0b\x32\x32.google.cloud.speech.v1.StreamingRecognitionConfigH\x00\x12\x17\n\raudio_content\x18\x02 \x01(\x0cH\x00\x42\x13\n\x11streaming_request\"\xa7\x03\n\x1aStreamingRecognitionConfig\x12>\n\x06\x63onfig\x18\x01 \x01(\x0b\x32).google.cloud.speech.v1.RecognitionConfigB\x03\xe0\x41\x02\x12\x18\n\x10single_utterance\x18\x02 \x01(\x08\x12\x17\n\x0finterim_results\x18\x03 \x01(\x08\x12$\n\x1c\x65nable_voice_activity_events\x18\x05 \x01(\x08\x12g\n\x16voice_activity_timeout\x18\x06 \x01(\x0b\x32G.google.cloud.speech.v1.StreamingRecognitionConfig.VoiceActivityTimeout\x1a\x86\x01\n\x14VoiceActivityTimeout\x12\x37\n\x14speech_start_timeout\x18\x01 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x35\n\x12speech_end_timeout\x18\x02 \x01(\x0b\x32\x19.google.protobuf.Duration\"\xe9\x07\n\x11RecognitionConfig\x12I\n\x08\x65ncoding\x18\x01 \x01(\x0e\x32\x37.google.cloud.speech.v1.RecognitionConfig.AudioEncoding\x12\x19\n\x11sample_rate_hertz\x18\x02 \x01(\x05\x12\x1b\n\x13\x61udio_channel_count\x18\x07 \x01(\x05\x12/\n\'enable_separate_recognition_per_channel\x18\x0c \x01(\x08\x12\x1a\n\rlanguage_code\x18\x03 \x01(\tB\x03\xe0\x41\x02\x12\"\n\x1a\x61lternative_language_codes\x18\x12 \x03(\t\x12\x18\n\x10max_alternatives\x18\x04 \x01(\x05\x12\x18\n\x10profanity_filter\x18\x05 \x01(\x08\x12<\n\nadaptation\x18\x14 \x01(\x0b\x32(.google.cloud.speech.v1.SpeechAdaptation\x12>\n\x0fspeech_contexts\x18\x06 \x03(\x0b\x32%.google.cloud.speech.v1.SpeechContext\x12 \n\x18\x65nable_word_time_offsets\x18\x08 \x01(\x08\x12\x1e\n\x16\x65nable_word_confidence\x18\x0f \x01(\x08\x12$\n\x1c\x65nable_automatic_punctuation\x18\x0b \x01(\x08\x12=\n\x19\x65nable_spoken_punctuation\x18\x16 \x01(\x0b\x32\x1a.google.protobuf.BoolValue\x12\x38\n\x14\x65nable_spoken_emojis\x18\x17 \x01(\x0b\x32\x1a.google.protobuf.BoolValue\x12L\n\x12\x64iarization_config\x18\x13 \x01(\x0b\x32\x30.google.cloud.speech.v1.SpeakerDiarizationConfig\x12=\n\x08metadata\x18\t \x01(\x0b\x32+.google.cloud.speech.v1.RecognitionMetadata\x12\r\n\x05model\x18\r \x01(\t\x12\x14\n\x0cuse_enhanced\x18\x0e \x01(\x08\"\x9a\x01\n\rAudioEncoding\x12\x18\n\x14\x45NCODING_UNSPECIFIED\x10\x00\x12\x0c\n\x08LINEAR16\x10\x01\x12\x08\n\x04\x46LAC\x10\x02\x12\t\n\x05MULAW\x10\x03\x12\x07\n\x03\x41MR\x10\x04\x12\n\n\x06\x41MR_WB\x10\x05\x12\x0c\n\x08OGG_OPUS\x10\x06\x12\x1a\n\x16SPEEX_WITH_HEADER_BYTE\x10\x07\x12\r\n\tWEBM_OPUS\x10\t\"\x90\x01\n\x18SpeakerDiarizationConfig\x12\"\n\x1a\x65nable_speaker_diarization\x18\x01 \x01(\x08\x12\x19\n\x11min_speaker_count\x18\x02 \x01(\x05\x12\x19\n\x11max_speaker_count\x18\x03 \x01(\x05\x12\x1a\n\x0bspeaker_tag\x18\x05 \x01(\x05\x42\x05\x18\x01\xe0\x41\x03\"\xa4\x08\n\x13RecognitionMetadata\x12U\n\x10interaction_type\x18\x01 \x01(\x0e\x32;.google.cloud.speech.v1.RecognitionMetadata.InteractionType\x12$\n\x1cindustry_naics_code_of_audio\x18\x03 \x01(\r\x12[\n\x13microphone_distance\x18\x04 \x01(\x0e\x32>.google.cloud.speech.v1.RecognitionMetadata.MicrophoneDistance\x12Z\n\x13original_media_type\x18\x05 \x01(\x0e\x32=.google.cloud.speech.v1.RecognitionMetadata.OriginalMediaType\x12^\n\x15recording_device_type\x18\x06 \x01(\x0e\x32?.google.cloud.speech.v1.RecognitionMetadata.RecordingDeviceType\x12\x1d\n\x15recording_device_name\x18\x07 \x01(\t\x12\x1a\n\x12original_mime_type\x18\x08 \x01(\t\x12\x13\n\x0b\x61udio_topic\x18\n \x01(\t\"\xc5\x01\n\x0fInteractionType\x12 \n\x1cINTERACTION_TYPE_UNSPECIFIED\x10\x00\x12\x0e\n\nDISCUSSION\x10\x01\x12\x10\n\x0cPRESENTATION\x10\x02\x12\x0e\n\nPHONE_CALL\x10\x03\x12\r\n\tVOICEMAIL\x10\x04\x12\x1b\n\x17PROFESSIONALLY_PRODUCED\x10\x05\x12\x10\n\x0cVOICE_SEARCH\x10\x06\x12\x11\n\rVOICE_COMMAND\x10\x07\x12\r\n\tDICTATION\x10\x08\"d\n\x12MicrophoneDistance\x12#\n\x1fMICROPHONE_DISTANCE_UNSPECIFIED\x10\x00\x12\r\n\tNEARFIELD\x10\x01\x12\x0c\n\x08MIDFIELD\x10\x02\x12\x0c\n\x08\x46\x41RFIELD\x10\x03\"N\n\x11OriginalMediaType\x12#\n\x1fORIGINAL_MEDIA_TYPE_UNSPECIFIED\x10\x00\x12\t\n\x05\x41UDIO\x10\x01\x12\t\n\x05VIDEO\x10\x02\"\xa4\x01\n\x13RecordingDeviceType\x12%\n!RECORDING_DEVICE_TYPE_UNSPECIFIED\x10\x00\x12\x0e\n\nSMARTPHONE\x10\x01\x12\x06\n\x02PC\x10\x02\x12\x0e\n\nPHONE_LINE\x10\x03\x12\x0b\n\x07VEHICLE\x10\x04\x12\x18\n\x14OTHER_OUTDOOR_DEVICE\x10\x05\x12\x17\n\x13OTHER_INDOOR_DEVICE\x10\x06:\x02\x18\x01\"/\n\rSpeechContext\x12\x0f\n\x07phrases\x18\x01 \x03(\t\x12\r\n\x05\x62oost\x18\x04 \x01(\x02\"D\n\x10RecognitionAudio\x12\x11\n\x07\x63ontent\x18\x01 \x01(\x0cH\x00\x12\r\n\x03uri\x18\x02 \x01(\tH\x00\x42\x0e\n\x0c\x61udio_source\"\xed\x01\n\x11RecognizeResponse\x12@\n\x07results\x18\x02 \x03(\x0b\x32/.google.cloud.speech.v1.SpeechRecognitionResult\x12\x34\n\x11total_billed_time\x18\x03 \x01(\x0b\x32\x19.google.protobuf.Duration\x12L\n\x16speech_adaptation_info\x18\x07 \x01(\x0b\x32,.google.cloud.speech.v1.SpeechAdaptationInfo\x12\x12\n\nrequest_id\x18\x08 \x01(\x03\"\xe9\x02\n\x1cLongRunningRecognizeResponse\x12@\n\x07results\x18\x02 \x03(\x0b\x32/.google.cloud.speech.v1.SpeechRecognitionResult\x12\x34\n\x11total_billed_time\x18\x03 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x45\n\routput_config\x18\x06 \x01(\x0b\x32..google.cloud.speech.v1.TranscriptOutputConfig\x12(\n\x0coutput_error\x18\x07 \x01(\x0b\x32\x12.google.rpc.Status\x12L\n\x16speech_adaptation_info\x18\x08 \x01(\x0b\x32,.google.cloud.speech.v1.SpeechAdaptationInfo\x12\x12\n\nrequest_id\x18\t \x01(\x03\"\xb0\x01\n\x1cLongRunningRecognizeMetadata\x12\x18\n\x10progress_percent\x18\x01 \x01(\x05\x12.\n\nstart_time\x18\x02 \x01(\x0b\x32\x1a.google.protobuf.Timestamp\x12\x34\n\x10last_update_time\x18\x03 \x01(\x0b\x32\x1a.google.protobuf.Timestamp\x12\x10\n\x03uri\x18\x04 \x01(\tB\x03\xe0\x41\x03\"\xd1\x04\n\x1aStreamingRecognizeResponse\x12!\n\x05\x65rror\x18\x01 \x01(\x0b\x32\x12.google.rpc.Status\x12\x43\n\x07results\x18\x02 \x03(\x0b\x32\x32.google.cloud.speech.v1.StreamingRecognitionResult\x12]\n\x11speech_event_type\x18\x04 \x01(\x0e\x32\x42.google.cloud.speech.v1.StreamingRecognizeResponse.SpeechEventType\x12\x34\n\x11speech_event_time\x18\x08 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x34\n\x11total_billed_time\x18\x05 \x01(\x0b\x32\x19.google.protobuf.Duration\x12L\n\x16speech_adaptation_info\x18\t \x01(\x0b\x32,.google.cloud.speech.v1.SpeechAdaptationInfo\x12\x12\n\nrequest_id\x18\n \x01(\x03\"\x9d\x01\n\x0fSpeechEventType\x12\x1c\n\x18SPEECH_EVENT_UNSPECIFIED\x10\x00\x12\x1b\n\x17\x45ND_OF_SINGLE_UTTERANCE\x10\x01\x12\x19\n\x15SPEECH_ACTIVITY_BEGIN\x10\x02\x12\x17\n\x13SPEECH_ACTIVITY_END\x10\x03\x12\x1b\n\x17SPEECH_ACTIVITY_TIMEOUT\x10\x04\"\xf2\x01\n\x1aStreamingRecognitionResult\x12J\n\x0c\x61lternatives\x18\x01 \x03(\x0b\x32\x34.google.cloud.speech.v1.SpeechRecognitionAlternative\x12\x10\n\x08is_final\x18\x02 \x01(\x08\x12\x11\n\tstability\x18\x03 \x01(\x02\x12\x32\n\x0fresult_end_time\x18\x04 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x13\n\x0b\x63hannel_tag\x18\x05 \x01(\x05\x12\x1a\n\rlanguage_code\x18\x06 \x01(\tB\x03\xe0\x41\x03\"\xca\x01\n\x17SpeechRecognitionResult\x12J\n\x0c\x61lternatives\x18\x01 \x03(\x0b\x32\x34.google.cloud.speech.v1.SpeechRecognitionAlternative\x12\x13\n\x0b\x63hannel_tag\x18\x02 \x01(\x05\x12\x32\n\x0fresult_end_time\x18\x04 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x1a\n\rlanguage_code\x18\x05 \x01(\tB\x03\xe0\x41\x03\"w\n\x1cSpeechRecognitionAlternative\x12\x12\n\ntranscript\x18\x01 \x01(\t\x12\x12\n\nconfidence\x18\x02 \x01(\x02\x12/\n\x05words\x18\x03 \x03(\x0b\x32 .google.cloud.speech.v1.WordInfo\"\xa2\x01\n\x08WordInfo\x12-\n\nstart_time\x18\x01 \x01(\x0b\x32\x19.google.protobuf.Duration\x12+\n\x08\x65nd_time\x18\x02 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x0c\n\x04word\x18\x03 \x01(\t\x12\x12\n\nconfidence\x18\x04 \x01(\x02\x12\x18\n\x0bspeaker_tag\x18\x05 \x01(\x05\x42\x03\xe0\x41\x03\"K\n\x14SpeechAdaptationInfo\x12\x1a\n\x12\x61\x64\x61ptation_timeout\x18\x01 \x01(\x08\x12\x17\n\x0ftimeout_message\x18\x04 \x01(\t2\xd1\x04\n\x06Speech\x12\x90\x01\n\tRecognize\x12(.google.cloud.speech.v1.RecognizeRequest\x1a).google.cloud.speech.v1.RecognizeResponse\".\x82\xd3\xe4\x93\x02\x19\"\x14/v1/speech:recognize:\x01*\xda\x41\x0c\x63onfig,audio\x12\xe4\x01\n\x14LongRunningRecognize\x12\x33.google.cloud.speech.v1.LongRunningRecognizeRequest\x1a\x1d.google.longrunning.Operation\"x\x82\xd3\xe4\x93\x02$\"\x1f/v1/speech:longrunningrecognize:\x01*\xda\x41\x0c\x63onfig,audio\xca\x41<\n\x1cLongRunningRecognizeResponse\x12\x1cLongRunningRecognizeMetadata\x12\x81\x01\n\x12StreamingRecognize\x12\x31.google.cloud.speech.v1.StreamingRecognizeRequest\x1a\x32.google.cloud.speech.v1.StreamingRecognizeResponse\"\x00(\x01\x30\x01\x1aI\xca\x41\x15speech.googleapis.com\xd2\x41.https://www.googleapis.com/auth/cloud-platformBh\n\x1a\x63om.google.cloud.speech.v1B\x0bSpeechProtoP\x01Z2cloud.google.com/go/speech/apiv1/speechpb;speechpb\xf8\x01\x01\xa2\x02\x03GCSb\x06proto3"
18
+ descriptor_data = "\n)google/cloud/speech/v1/cloud_speech.proto\x12\x16google.cloud.speech.v1\x1a\x1cgoogle/api/annotations.proto\x1a\x17google/api/client.proto\x1a\x1fgoogle/api/field_behavior.proto\x1a%google/cloud/speech/v1/resource.proto\x1a#google/longrunning/operations.proto\x1a\x1egoogle/protobuf/duration.proto\x1a\x1fgoogle/protobuf/timestamp.proto\x1a\x1egoogle/protobuf/wrappers.proto\x1a\x17google/rpc/status.proto\"\x90\x01\n\x10RecognizeRequest\x12>\n\x06\x63onfig\x18\x01 \x01(\x0b\x32).google.cloud.speech.v1.RecognitionConfigB\x03\xe0\x41\x02\x12<\n\x05\x61udio\x18\x02 \x01(\x0b\x32(.google.cloud.speech.v1.RecognitionAudioB\x03\xe0\x41\x02\"\xe7\x01\n\x1bLongRunningRecognizeRequest\x12>\n\x06\x63onfig\x18\x01 \x01(\x0b\x32).google.cloud.speech.v1.RecognitionConfigB\x03\xe0\x41\x02\x12<\n\x05\x61udio\x18\x02 \x01(\x0b\x32(.google.cloud.speech.v1.RecognitionAudioB\x03\xe0\x41\x02\x12J\n\routput_config\x18\x04 \x01(\x0b\x32..google.cloud.speech.v1.TranscriptOutputConfigB\x03\xe0\x41\x01\":\n\x16TranscriptOutputConfig\x12\x11\n\x07gcs_uri\x18\x01 \x01(\tH\x00\x42\r\n\x0boutput_type\"\x99\x01\n\x19StreamingRecognizeRequest\x12N\n\x10streaming_config\x18\x01 \x01(\x0b\x32\x32.google.cloud.speech.v1.StreamingRecognitionConfigH\x00\x12\x17\n\raudio_content\x18\x02 \x01(\x0cH\x00\x42\x13\n\x11streaming_request\"\xa7\x03\n\x1aStreamingRecognitionConfig\x12>\n\x06\x63onfig\x18\x01 \x01(\x0b\x32).google.cloud.speech.v1.RecognitionConfigB\x03\xe0\x41\x02\x12\x18\n\x10single_utterance\x18\x02 \x01(\x08\x12\x17\n\x0finterim_results\x18\x03 \x01(\x08\x12$\n\x1c\x65nable_voice_activity_events\x18\x05 \x01(\x08\x12g\n\x16voice_activity_timeout\x18\x06 \x01(\x0b\x32G.google.cloud.speech.v1.StreamingRecognitionConfig.VoiceActivityTimeout\x1a\x86\x01\n\x14VoiceActivityTimeout\x12\x37\n\x14speech_start_timeout\x18\x01 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x35\n\x12speech_end_timeout\x18\x02 \x01(\x0b\x32\x19.google.protobuf.Duration\"\xca\x08\n\x11RecognitionConfig\x12I\n\x08\x65ncoding\x18\x01 \x01(\x0e\x32\x37.google.cloud.speech.v1.RecognitionConfig.AudioEncoding\x12\x19\n\x11sample_rate_hertz\x18\x02 \x01(\x05\x12\x1b\n\x13\x61udio_channel_count\x18\x07 \x01(\x05\x12/\n\'enable_separate_recognition_per_channel\x18\x0c \x01(\x08\x12\x1a\n\rlanguage_code\x18\x03 \x01(\tB\x03\xe0\x41\x02\x12\"\n\x1a\x61lternative_language_codes\x18\x12 \x03(\t\x12\x18\n\x10max_alternatives\x18\x04 \x01(\x05\x12\x18\n\x10profanity_filter\x18\x05 \x01(\x08\x12<\n\nadaptation\x18\x14 \x01(\x0b\x32(.google.cloud.speech.v1.SpeechAdaptation\x12V\n\x18transcript_normalization\x18\x18 \x01(\x0b\x32/.google.cloud.speech.v1.TranscriptNormalizationB\x03\xe0\x41\x01\x12>\n\x0fspeech_contexts\x18\x06 \x03(\x0b\x32%.google.cloud.speech.v1.SpeechContext\x12 \n\x18\x65nable_word_time_offsets\x18\x08 \x01(\x08\x12\x1e\n\x16\x65nable_word_confidence\x18\x0f \x01(\x08\x12$\n\x1c\x65nable_automatic_punctuation\x18\x0b \x01(\x08\x12=\n\x19\x65nable_spoken_punctuation\x18\x16 \x01(\x0b\x32\x1a.google.protobuf.BoolValue\x12\x38\n\x14\x65nable_spoken_emojis\x18\x17 \x01(\x0b\x32\x1a.google.protobuf.BoolValue\x12L\n\x12\x64iarization_config\x18\x13 \x01(\x0b\x32\x30.google.cloud.speech.v1.SpeakerDiarizationConfig\x12=\n\x08metadata\x18\t \x01(\x0b\x32+.google.cloud.speech.v1.RecognitionMetadata\x12\r\n\x05model\x18\r \x01(\t\x12\x14\n\x0cuse_enhanced\x18\x0e \x01(\x08\"\xa3\x01\n\rAudioEncoding\x12\x18\n\x14\x45NCODING_UNSPECIFIED\x10\x00\x12\x0c\n\x08LINEAR16\x10\x01\x12\x08\n\x04\x46LAC\x10\x02\x12\t\n\x05MULAW\x10\x03\x12\x07\n\x03\x41MR\x10\x04\x12\n\n\x06\x41MR_WB\x10\x05\x12\x0c\n\x08OGG_OPUS\x10\x06\x12\x1a\n\x16SPEEX_WITH_HEADER_BYTE\x10\x07\x12\x07\n\x03MP3\x10\x08\x12\r\n\tWEBM_OPUS\x10\t\"\x90\x01\n\x18SpeakerDiarizationConfig\x12\"\n\x1a\x65nable_speaker_diarization\x18\x01 \x01(\x08\x12\x19\n\x11min_speaker_count\x18\x02 \x01(\x05\x12\x19\n\x11max_speaker_count\x18\x03 \x01(\x05\x12\x1a\n\x0bspeaker_tag\x18\x05 \x01(\x05\x42\x05\x18\x01\xe0\x41\x03\"\xa4\x08\n\x13RecognitionMetadata\x12U\n\x10interaction_type\x18\x01 \x01(\x0e\x32;.google.cloud.speech.v1.RecognitionMetadata.InteractionType\x12$\n\x1cindustry_naics_code_of_audio\x18\x03 \x01(\r\x12[\n\x13microphone_distance\x18\x04 \x01(\x0e\x32>.google.cloud.speech.v1.RecognitionMetadata.MicrophoneDistance\x12Z\n\x13original_media_type\x18\x05 \x01(\x0e\x32=.google.cloud.speech.v1.RecognitionMetadata.OriginalMediaType\x12^\n\x15recording_device_type\x18\x06 \x01(\x0e\x32?.google.cloud.speech.v1.RecognitionMetadata.RecordingDeviceType\x12\x1d\n\x15recording_device_name\x18\x07 \x01(\t\x12\x1a\n\x12original_mime_type\x18\x08 \x01(\t\x12\x13\n\x0b\x61udio_topic\x18\n \x01(\t\"\xc5\x01\n\x0fInteractionType\x12 \n\x1cINTERACTION_TYPE_UNSPECIFIED\x10\x00\x12\x0e\n\nDISCUSSION\x10\x01\x12\x10\n\x0cPRESENTATION\x10\x02\x12\x0e\n\nPHONE_CALL\x10\x03\x12\r\n\tVOICEMAIL\x10\x04\x12\x1b\n\x17PROFESSIONALLY_PRODUCED\x10\x05\x12\x10\n\x0cVOICE_SEARCH\x10\x06\x12\x11\n\rVOICE_COMMAND\x10\x07\x12\r\n\tDICTATION\x10\x08\"d\n\x12MicrophoneDistance\x12#\n\x1fMICROPHONE_DISTANCE_UNSPECIFIED\x10\x00\x12\r\n\tNEARFIELD\x10\x01\x12\x0c\n\x08MIDFIELD\x10\x02\x12\x0c\n\x08\x46\x41RFIELD\x10\x03\"N\n\x11OriginalMediaType\x12#\n\x1fORIGINAL_MEDIA_TYPE_UNSPECIFIED\x10\x00\x12\t\n\x05\x41UDIO\x10\x01\x12\t\n\x05VIDEO\x10\x02\"\xa4\x01\n\x13RecordingDeviceType\x12%\n!RECORDING_DEVICE_TYPE_UNSPECIFIED\x10\x00\x12\x0e\n\nSMARTPHONE\x10\x01\x12\x06\n\x02PC\x10\x02\x12\x0e\n\nPHONE_LINE\x10\x03\x12\x0b\n\x07VEHICLE\x10\x04\x12\x18\n\x14OTHER_OUTDOOR_DEVICE\x10\x05\x12\x17\n\x13OTHER_INDOOR_DEVICE\x10\x06:\x02\x18\x01\"/\n\rSpeechContext\x12\x0f\n\x07phrases\x18\x01 \x03(\t\x12\r\n\x05\x62oost\x18\x04 \x01(\x02\"D\n\x10RecognitionAudio\x12\x11\n\x07\x63ontent\x18\x01 \x01(\x0cH\x00\x12\r\n\x03uri\x18\x02 \x01(\tH\x00\x42\x0e\n\x0c\x61udio_source\"\xed\x01\n\x11RecognizeResponse\x12@\n\x07results\x18\x02 \x03(\x0b\x32/.google.cloud.speech.v1.SpeechRecognitionResult\x12\x34\n\x11total_billed_time\x18\x03 \x01(\x0b\x32\x19.google.protobuf.Duration\x12L\n\x16speech_adaptation_info\x18\x07 \x01(\x0b\x32,.google.cloud.speech.v1.SpeechAdaptationInfo\x12\x12\n\nrequest_id\x18\x08 \x01(\x03\"\xe9\x02\n\x1cLongRunningRecognizeResponse\x12@\n\x07results\x18\x02 \x03(\x0b\x32/.google.cloud.speech.v1.SpeechRecognitionResult\x12\x34\n\x11total_billed_time\x18\x03 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x45\n\routput_config\x18\x06 \x01(\x0b\x32..google.cloud.speech.v1.TranscriptOutputConfig\x12(\n\x0coutput_error\x18\x07 \x01(\x0b\x32\x12.google.rpc.Status\x12L\n\x16speech_adaptation_info\x18\x08 \x01(\x0b\x32,.google.cloud.speech.v1.SpeechAdaptationInfo\x12\x12\n\nrequest_id\x18\t \x01(\x03\"\xb0\x01\n\x1cLongRunningRecognizeMetadata\x12\x18\n\x10progress_percent\x18\x01 \x01(\x05\x12.\n\nstart_time\x18\x02 \x01(\x0b\x32\x1a.google.protobuf.Timestamp\x12\x34\n\x10last_update_time\x18\x03 \x01(\x0b\x32\x1a.google.protobuf.Timestamp\x12\x10\n\x03uri\x18\x04 \x01(\tB\x03\xe0\x41\x03\"\xd1\x04\n\x1aStreamingRecognizeResponse\x12!\n\x05\x65rror\x18\x01 \x01(\x0b\x32\x12.google.rpc.Status\x12\x43\n\x07results\x18\x02 \x03(\x0b\x32\x32.google.cloud.speech.v1.StreamingRecognitionResult\x12]\n\x11speech_event_type\x18\x04 \x01(\x0e\x32\x42.google.cloud.speech.v1.StreamingRecognizeResponse.SpeechEventType\x12\x34\n\x11speech_event_time\x18\x08 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x34\n\x11total_billed_time\x18\x05 \x01(\x0b\x32\x19.google.protobuf.Duration\x12L\n\x16speech_adaptation_info\x18\t \x01(\x0b\x32,.google.cloud.speech.v1.SpeechAdaptationInfo\x12\x12\n\nrequest_id\x18\n \x01(\x03\"\x9d\x01\n\x0fSpeechEventType\x12\x1c\n\x18SPEECH_EVENT_UNSPECIFIED\x10\x00\x12\x1b\n\x17\x45ND_OF_SINGLE_UTTERANCE\x10\x01\x12\x19\n\x15SPEECH_ACTIVITY_BEGIN\x10\x02\x12\x17\n\x13SPEECH_ACTIVITY_END\x10\x03\x12\x1b\n\x17SPEECH_ACTIVITY_TIMEOUT\x10\x04\"\xf2\x01\n\x1aStreamingRecognitionResult\x12J\n\x0c\x61lternatives\x18\x01 \x03(\x0b\x32\x34.google.cloud.speech.v1.SpeechRecognitionAlternative\x12\x10\n\x08is_final\x18\x02 \x01(\x08\x12\x11\n\tstability\x18\x03 \x01(\x02\x12\x32\n\x0fresult_end_time\x18\x04 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x13\n\x0b\x63hannel_tag\x18\x05 \x01(\x05\x12\x1a\n\rlanguage_code\x18\x06 \x01(\tB\x03\xe0\x41\x03\"\xca\x01\n\x17SpeechRecognitionResult\x12J\n\x0c\x61lternatives\x18\x01 \x03(\x0b\x32\x34.google.cloud.speech.v1.SpeechRecognitionAlternative\x12\x13\n\x0b\x63hannel_tag\x18\x02 \x01(\x05\x12\x32\n\x0fresult_end_time\x18\x04 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x1a\n\rlanguage_code\x18\x05 \x01(\tB\x03\xe0\x41\x03\"w\n\x1cSpeechRecognitionAlternative\x12\x12\n\ntranscript\x18\x01 \x01(\t\x12\x12\n\nconfidence\x18\x02 \x01(\x02\x12/\n\x05words\x18\x03 \x03(\x0b\x32 .google.cloud.speech.v1.WordInfo\"\xc0\x01\n\x08WordInfo\x12-\n\nstart_time\x18\x01 \x01(\x0b\x32\x19.google.protobuf.Duration\x12+\n\x08\x65nd_time\x18\x02 \x01(\x0b\x32\x19.google.protobuf.Duration\x12\x0c\n\x04word\x18\x03 \x01(\t\x12\x12\n\nconfidence\x18\x04 \x01(\x02\x12\x1a\n\x0bspeaker_tag\x18\x05 \x01(\x05\x42\x05\x18\x01\xe0\x41\x03\x12\x1a\n\rspeaker_label\x18\x06 \x01(\tB\x03\xe0\x41\x03\"K\n\x14SpeechAdaptationInfo\x12\x1a\n\x12\x61\x64\x61ptation_timeout\x18\x01 \x01(\x08\x12\x17\n\x0ftimeout_message\x18\x04 \x01(\t2\xd1\x04\n\x06Speech\x12\x90\x01\n\tRecognize\x12(.google.cloud.speech.v1.RecognizeRequest\x1a).google.cloud.speech.v1.RecognizeResponse\".\x82\xd3\xe4\x93\x02\x19\"\x14/v1/speech:recognize:\x01*\xda\x41\x0c\x63onfig,audio\x12\xe4\x01\n\x14LongRunningRecognize\x12\x33.google.cloud.speech.v1.LongRunningRecognizeRequest\x1a\x1d.google.longrunning.Operation\"x\x82\xd3\xe4\x93\x02$\"\x1f/v1/speech:longrunningrecognize:\x01*\xda\x41\x0c\x63onfig,audio\xca\x41<\n\x1cLongRunningRecognizeResponse\x12\x1cLongRunningRecognizeMetadata\x12\x81\x01\n\x12StreamingRecognize\x12\x31.google.cloud.speech.v1.StreamingRecognizeRequest\x1a\x32.google.cloud.speech.v1.StreamingRecognizeResponse\"\x00(\x01\x30\x01\x1aI\xca\x41\x15speech.googleapis.com\xd2\x41.https://www.googleapis.com/auth/cloud-platformBh\n\x1a\x63om.google.cloud.speech.v1B\x0bSpeechProtoP\x01Z2cloud.google.com/go/speech/apiv1/speechpb;speechpb\xf8\x01\x01\xa2\x02\x03GCSb\x06proto3"
19
19
 
20
20
  pool = Google::Protobuf::DescriptorPool.generated_pool
21
21
 
data/lib/google/cloud/speech/v1/resource_pb.rb CHANGED
@@ -7,7 +7,7 @@ require 'google/protobuf'
7
7
  require 'google/api/resource_pb'
8
8
 
9
9
 
10
- descriptor_data = "\n%google/cloud/speech/v1/resource.proto\x12\x16google.cloud.speech.v1\x1a\x19google/api/resource.proto\"\xfc\x01\n\x0b\x43ustomClass\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x17\n\x0f\x63ustom_class_id\x18\x02 \x01(\t\x12<\n\x05items\x18\x03 \x03(\x0b\x32-.google.cloud.speech.v1.CustomClass.ClassItem\x1a\x1a\n\tClassItem\x12\r\n\x05value\x18\x01 \x01(\t:l\xea\x41i\n!speech.googleapis.com/CustomClass\x12\x44projects/{project}/locations/{location}/customClasses/{custom_class}\"\xf2\x01\n\tPhraseSet\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x39\n\x07phrases\x18\x02 \x03(\x0b\x32(.google.cloud.speech.v1.PhraseSet.Phrase\x12\r\n\x05\x62oost\x18\x04 \x01(\x02\x1a&\n\x06Phrase\x12\r\n\x05value\x18\x01 \x01(\t\x12\r\n\x05\x62oost\x18\x02 \x01(\x02:e\xea\x41\x62\n\x1fspeech.googleapis.com/PhraseSet\x12?projects/{project}/locations/{location}/phraseSets/{phrase_set}\"\xbd\x02\n\x10SpeechAdaptation\x12\x36\n\x0bphrase_sets\x18\x01 \x03(\x0b\x32!.google.cloud.speech.v1.PhraseSet\x12\x43\n\x15phrase_set_references\x18\x02 \x03(\tB$\xfa\x41!\n\x1fspeech.googleapis.com/PhraseSet\x12;\n\x0e\x63ustom_classes\x18\x03 \x03(\x0b\x32#.google.cloud.speech.v1.CustomClass\x12J\n\x0c\x61\x62nf_grammar\x18\x04 \x01(\x0b\x32\x34.google.cloud.speech.v1.SpeechAdaptation.ABNFGrammar\x1a#\n\x0b\x41\x42NFGrammar\x12\x14\n\x0c\x61\x62nf_strings\x18\x01 \x03(\tBp\n\x1a\x63om.google.cloud.speech.v1B\x13SpeechResourceProtoP\x01Z2cloud.google.com/go/speech/apiv1/speechpb;speechpb\xf8\x01\x01\xa2\x02\x03GCSb\x06proto3"
10
+ descriptor_data = "\n%google/cloud/speech/v1/resource.proto\x12\x16google.cloud.speech.v1\x1a\x19google/api/resource.proto\"\xfc\x01\n\x0b\x43ustomClass\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x17\n\x0f\x63ustom_class_id\x18\x02 \x01(\t\x12<\n\x05items\x18\x03 \x03(\x0b\x32-.google.cloud.speech.v1.CustomClass.ClassItem\x1a\x1a\n\tClassItem\x12\r\n\x05value\x18\x01 \x01(\t:l\xea\x41i\n!speech.googleapis.com/CustomClass\x12\x44projects/{project}/locations/{location}/customClasses/{custom_class}\"\xf2\x01\n\tPhraseSet\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x39\n\x07phrases\x18\x02 \x03(\x0b\x32(.google.cloud.speech.v1.PhraseSet.Phrase\x12\r\n\x05\x62oost\x18\x04 \x01(\x02\x1a&\n\x06Phrase\x12\r\n\x05value\x18\x01 \x01(\t\x12\r\n\x05\x62oost\x18\x02 \x01(\x02:e\xea\x41\x62\n\x1fspeech.googleapis.com/PhraseSet\x12?projects/{project}/locations/{location}/phraseSets/{phrase_set}\"\xbd\x02\n\x10SpeechAdaptation\x12\x36\n\x0bphrase_sets\x18\x01 \x03(\x0b\x32!.google.cloud.speech.v1.PhraseSet\x12\x43\n\x15phrase_set_references\x18\x02 \x03(\tB$\xfa\x41!\n\x1fspeech.googleapis.com/PhraseSet\x12;\n\x0e\x63ustom_classes\x18\x03 \x03(\x0b\x32#.google.cloud.speech.v1.CustomClass\x12J\n\x0c\x61\x62nf_grammar\x18\x04 \x01(\x0b\x32\x34.google.cloud.speech.v1.SpeechAdaptation.ABNFGrammar\x1a#\n\x0b\x41\x42NFGrammar\x12\x14\n\x0c\x61\x62nf_strings\x18\x01 \x03(\t\"\xa3\x01\n\x17TranscriptNormalization\x12\x46\n\x07\x65ntries\x18\x01 \x03(\x0b\x32\x35.google.cloud.speech.v1.TranscriptNormalization.Entry\x1a@\n\x05\x45ntry\x12\x0e\n\x06search\x18\x01 \x01(\t\x12\x0f\n\x07replace\x18\x02 \x01(\t\x12\x16\n\x0e\x63\x61se_sensitive\x18\x03 \x01(\x08\x42p\n\x1a\x63om.google.cloud.speech.v1B\x13SpeechResourceProtoP\x01Z2cloud.google.com/go/speech/apiv1/speechpb;speechpb\xf8\x01\x01\xa2\x02\x03GCSb\x06proto3"
11
11
 
12
12
  pool = Google::Protobuf::DescriptorPool.generated_pool
13
13
 
@@ -43,6 +43,8 @@ module Google
43
43
  PhraseSet::Phrase = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.PhraseSet.Phrase").msgclass
44
44
  SpeechAdaptation = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.SpeechAdaptation").msgclass
45
45
  SpeechAdaptation::ABNFGrammar = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.SpeechAdaptation.ABNFGrammar").msgclass
46
+ TranscriptNormalization = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.TranscriptNormalization").msgclass
47
+ TranscriptNormalization::Entry = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1.TranscriptNormalization.Entry").msgclass
46
48
  end
47
49
  end
48
50
  end
data/lib/google/cloud/speech/v1/version.rb CHANGED
@@ -21,7 +21,7 @@ module Google
21
21
  module Cloud
22
22
  module Speech
23
23
  module V1
24
- VERSION = "0.14.0"
24
+ VERSION = "0.15.0"
25
25
  end
26
26
  end
27
27
  end
data/proto_docs/google/cloud/speech/v1/cloud_speech.rb CHANGED
@@ -227,6 +227,12 @@ module Google
227
227
  # adaptation](https://cloud.google.com/speech-to-text/docs/adaptation)
228
228
  # documentation.
229
229
  # When speech adaptation is set it supersedes the `speech_contexts` field.
230
+ # @!attribute [rw] transcript_normalization
231
+ # @return [::Google::Cloud::Speech::V1::TranscriptNormalization]
232
+ # Optional. Use transcription normalization to automatically replace parts of
233
+ # the transcript with phrases of your choosing. For StreamingRecognize, this
234
+ # normalization only applies to stable partial transcripts (stability > 0.8)
235
+ # and final transcripts.
230
236
  # @!attribute [rw] speech_contexts
231
237
  # @return [::Array<::Google::Cloud::Speech::V1::SpeechContext>]
232
238
  # Array of {::Google::Cloud::Speech::V1::SpeechContext SpeechContext}.
@@ -415,6 +421,12 @@ module Google
415
421
  # wideband is supported. `sample_rate_hertz` must be 16000.
416
422
  SPEEX_WITH_HEADER_BYTE = 7
417
423
 
424
+ # MP3 audio. MP3 encoding is a Beta feature and only available in
425
+ # v1p1beta1. Support all standard MP3 bitrates (which range from 32-320
426
+ # kbps). When using this encoding, `sample_rate_hertz` has to match the
427
+ # sample rate of the file being used.
428
+ MP3 = 8
429
+
418
430
  # Opus encoded audio frames in WebM container
419
431
  # ([OggOpus](https://wiki.xiph.org/OggOpus)). `sample_rate_hertz` must be
420
432
  # one of 8000, 12000, 16000, 24000, or 48000.
@@ -426,8 +438,8 @@ module Google
426
438
  # @!attribute [rw] enable_speaker_diarization
427
439
  # @return [::Boolean]
428
440
  # If 'true', enables speaker detection for each recognized word in
429
- # the top alternative of the recognition result using a speaker_tag provided
430
- # in the WordInfo.
441
+ # the top alternative of the recognition result using a speaker_label
442
+ # provided in the WordInfo.
431
443
  # @!attribute [rw] min_speaker_count
432
444
  # @return [::Integer]
433
445
  # Minimum number of speakers in the conversation. This range gives you more
@@ -945,8 +957,17 @@ module Google
945
957
  # Output only. A distinct integer value is assigned for every speaker within
946
958
  # the audio. This field specifies which one of those speakers was detected to
947
959
  # have spoken this word. Value ranges from '1' to diarization_speaker_count.
948
- # speaker_tag is set if enable_speaker_diarization = 'true' and only in the
960
+ # speaker_tag is set if enable_speaker_diarization = 'true' and only for the
949
961
  # top alternative.
962
+ # Note: Use speaker_label instead.
963
+ # @!attribute [r] speaker_label
964
+ # @return [::String]
965
+ # Output only. A label value assigned for every unique speaker within the
966
+ # audio. This field specifies which speaker was detected to have spoken this
967
+ # word. For some models, like medical_conversation this can be actual speaker
968
+ # role, for example "patient" or "provider", but generally this would be a
969
+ # number identifying a speaker. This field is only set if
970
+ # enable_speaker_diarization = 'true' and only for the top alternative.
950
971
  class WordInfo
951
972
  include ::Google::Protobuf::MessageExts
952
973
  extend ::Google::Protobuf::MessageExts::ClassMethods
data/proto_docs/google/cloud/speech/v1/resource.rb CHANGED
@@ -149,6 +149,36 @@ module Google
149
149
  extend ::Google::Protobuf::MessageExts::ClassMethods
150
150
  end
151
151
  end
152
+
153
+ # Transcription normalization configuration. Use transcription normalization
154
+ # to automatically replace parts of the transcript with phrases of your
155
+ # choosing. For StreamingRecognize, this normalization only applies to stable
156
+ # partial transcripts (stability > 0.8) and final transcripts.
157
+ # @!attribute [rw] entries
158
+ # @return [::Array<::Google::Cloud::Speech::V1::TranscriptNormalization::Entry>]
159
+ # A list of replacement entries. We will perform replacement with one entry
160
+ # at a time. For example, the second entry in ["cat" => "dog", "mountain cat"
161
+ # => "mountain dog"] will never be applied because we will always process the
162
+ # first entry before it. At most 100 entries.
163
+ class TranscriptNormalization
164
+ include ::Google::Protobuf::MessageExts
165
+ extend ::Google::Protobuf::MessageExts::ClassMethods
166
+
167
+ # A single replacement configuration.
168
+ # @!attribute [rw] search
169
+ # @return [::String]
170
+ # What to replace. Max length is 100 characters.
171
+ # @!attribute [rw] replace
172
+ # @return [::String]
173
+ # What to replace with. Max length is 100 characters.
174
+ # @!attribute [rw] case_sensitive
175
+ # @return [::Boolean]
176
+ # Whether the search is case sensitive.
177
+ class Entry
178
+ include ::Google::Protobuf::MessageExts
179
+ extend ::Google::Protobuf::MessageExts::ClassMethods
180
+ end
181
+ end
152
182
  end
153
183
  end
154
184
  end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: google-cloud-speech-v1
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.14.0
4
+ version: 0.15.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Google LLC
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2023-09-12 00:00:00.000000000 Z
11
+ date: 2023-11-06 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: gapic-common