From e496559c17e00a1fb3989c6c38cb87a0453c5b29 Mon Sep 17 00:00:00 2001 From: Yoshi Automation Bot Date: Tue, 27 Apr 2021 12:10:16 -0700 Subject: [PATCH] feat: add webm opus support (#500) This PR was generated using Autosynth. :rainbow: Synth log will be available here: https://source.cloud.google.com/results/invocations/c65c7773-dbef-42eb-b70e-47092f05bd1b/targets - [ ] To automatically regenerate this PR, check this box. (May take up to 24 hours.) PiperOrigin-RevId: 370523741 Source-Link: https://github.com/googleapis/googleapis/commit/36a84fe3eaf841f56c4b6683d1c0403f7b503092 --- .../speech/v1p1beta1/RecognitionConfig.java | 42 +++- .../v1p1beta1/RecognitionConfigOrBuilder.java | 4 +- .../cloud/speech/v1p1beta1/SpeechProto.java | 191 +++++++++--------- .../cloud/speech/v1p1beta1/cloud_speech.proto | 9 +- synth.metadata | 10 +- 5 files changed, 145 insertions(+), 111 deletions(-) diff --git a/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfig.java b/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfig.java index 6a6aec931..1799127be 100644 --- a/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfig.java +++ b/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfig.java @@ -435,6 +435,19 @@ public enum AudioEncoding implements com.google.protobuf.ProtocolMessageEnum { * MP3 = 8; */ MP3(8), + /** + * + * + * 
+     * Opus encoded audio frames in WebM container
+     * ([OggOpus](https://wiki.xiph.org/OggOpus)). This is a Beta features and
+     * only available in v1p1beta1. `sample_rate_hertz` must be one of 8000,
+     * 12000, 16000, 24000, or 48000.
+     *
+ * + * WEBM_OPUS = 9; + */ + WEBM_OPUS(9), UNRECOGNIZED(-1), ; @@ -550,6 +563,19 @@ public enum AudioEncoding implements com.google.protobuf.ProtocolMessageEnum { * MP3 = 8; */ public static final int MP3_VALUE = 8; + /** + * + * + * 
+     * Opus encoded audio frames in WebM container
+     * ([OggOpus](https://wiki.xiph.org/OggOpus)). This is a Beta features and
+     * only available in v1p1beta1. `sample_rate_hertz` must be one of 8000,
+     * 12000, 16000, 24000, or 48000.
+     *
+ * + * WEBM_OPUS = 9; + */ + public static final int WEBM_OPUS_VALUE = 9; public final int getNumber() { if (this == UNRECOGNIZED) { @@ -593,6 +619,8 @@ public static AudioEncoding forNumber(int value) { return SPEEX_WITH_HEADER_BYTE; case 8: return MP3; + case 9: + return WEBM_OPUS; default: return null; } @@ -1496,7 +1524,7 @@ public com.google.cloud.speech.v1p1beta1.RecognitionMetadataOrBuilder getMetadat * </tr> * <tr> * <td><code>video</code></td> - * <td>Best for audio that originated from from video or includes multiple + * <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> @@ -1550,7 +1578,7 @@ public java.lang.String getModel() { * </tr> * <tr> * <td><code>video</code></td> - * <td>Best for audio that originated from from video or includes multiple + * <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> @@ -5094,7 +5122,7 @@ public com.google.cloud.speech.v1p1beta1.RecognitionMetadataOrBuilder getMetadat * </tr> * <tr> * <td><code>video</code></td> - * <td>Best for audio that originated from from video or includes multiple + * <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> @@ -5147,7 +5175,7 @@ public java.lang.String getModel() { * </tr> * <tr> * <td><code>video</code></td> - * <td>Best for audio that originated from from video or includes multiple + * <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> @@ -5200,7 +5228,7 @@ public com.google.protobuf.ByteString getModelBytes() { * </tr> * <tr> * <td><code>video</code></td> - * <td>Best for audio that originated from from video or includes multiple + * <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> @@ -5252,7 +5280,7 @@ public Builder setModel(java.lang.String value) { * </tr> * <tr> * <td><code>video</code></td> - * <td>Best for audio that originated from from video or includes multiple + * <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> @@ -5300,7 +5328,7 @@ public Builder clearModel() { * </tr> * <tr> * <td><code>video</code></td> - * <td>Best for audio that originated from from video or includes multiple + * <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> diff --git a/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfigOrBuilder.java b/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfigOrBuilder.java index 2502f4b4f..99350d004 100644 --- a/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfigOrBuilder.java +++ b/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfigOrBuilder.java @@ -689,7 +689,7 @@ public interface RecognitionConfigOrBuilder * </tr> * <tr> * <td><code>video</code></td> - * <td>Best for audio that originated from from video or includes multiple + * <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> @@ -732,7 +732,7 @@ public interface RecognitionConfigOrBuilder * </tr> * <tr> * <td><code>video</code></td> - * <td>Best for audio that originated from from video or includes multiple + * <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> diff --git a/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechProto.java b/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechProto.java index 41f71dbcd..18d17f440 100644 --- a/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechProto.java +++ b/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechProto.java @@ -137,7 +137,7 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() { + "\"\226\001\n\032StreamingRecognitionConfig\022E\n\006confi" + "g\030\001 \001(\01320.google.cloud.speech.v1p1beta1." + "RecognitionConfigB\003\340A\002\022\030\n\020single_utteran" - + "ce\030\002 \001(\010\022\027\n\017interim_results\030\003 \001(\010\"\325\010\n\021Re" + + "ce\030\002 \001(\010\022\027\n\017interim_results\030\003 \001(\010\"\344\010\n\021Re" + "cognitionConfig\022P\n\010encoding\030\001 \001(\0162>.goog" + "le.cloud.speech.v1p1beta1.RecognitionCon" + "fig.AudioEncoding\022\031\n\021sample_rate_hertz\030\002" @@ -161,105 +161,106 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() { + "cloud.speech.v1p1beta1.SpeakerDiarizatio" + "nConfig\022D\n\010metadata\030\t \001(\01322.google.cloud" + ".speech.v1p1beta1.RecognitionMetadata\022\r\n" - + "\005model\030\r \001(\t\022\024\n\014use_enhanced\030\016 \001(\010\"\224\001\n\rA" + + "\005model\030\r \001(\t\022\024\n\014use_enhanced\030\016 \001(\010\"\243\001\n\rA" + "udioEncoding\022\030\n\024ENCODING_UNSPECIFIED\020\000\022\014" + "\n\010LINEAR16\020\001\022\010\n\004FLAC\020\002\022\t\n\005MULAW\020\003\022\007\n\003AMR" + "\020\004\022\n\n\006AMR_WB\020\005\022\014\n\010OGG_OPUS\020\006\022\032\n\026SPEEX_WI" - + "TH_HEADER_BYTE\020\007\022\007\n\003MP3\020\010\"\220\001\n\030SpeakerDia" - + "rizationConfig\022\"\n\032enable_speaker_diariza" - + "tion\030\001 \001(\010\022\031\n\021min_speaker_count\030\002 \001(\005\022\031\n" - + "\021max_speaker_count\030\003 \001(\005\022\032\n\013speaker_tag\030" - + "\005 \001(\005B\005\030\001\340A\003\"\327\010\n\023RecognitionMetadata\022\\\n\020" - + "interaction_type\030\001 \001(\0162B.google.cloud.sp" - + "eech.v1p1beta1.RecognitionMetadata.Inter" - + "actionType\022$\n\034industry_naics_code_of_aud" - + "io\030\003 \001(\r\022b\n\023microphone_distance\030\004 \001(\0162E." + + "TH_HEADER_BYTE\020\007\022\007\n\003MP3\020\010\022\r\n\tWEBM_OPUS\020\t" + + "\"\220\001\n\030SpeakerDiarizationConfig\022\"\n\032enable_" + + "speaker_diarization\030\001 \001(\010\022\031\n\021min_speaker" + + "_count\030\002 \001(\005\022\031\n\021max_speaker_count\030\003 \001(\005\022" + + "\032\n\013speaker_tag\030\005 \001(\005B\005\030\001\340A\003\"\327\010\n\023Recognit" + + "ionMetadata\022\\\n\020interaction_type\030\001 \001(\0162B." + "google.cloud.speech.v1p1beta1.Recognitio" - + "nMetadata.MicrophoneDistance\022a\n\023original" - + "_media_type\030\005 \001(\0162D.google.cloud.speech." - + "v1p1beta1.RecognitionMetadata.OriginalMe" - + "diaType\022e\n\025recording_device_type\030\006 \001(\0162F" - + ".google.cloud.speech.v1p1beta1.Recogniti" - + "onMetadata.RecordingDeviceType\022\035\n\025record" - + "ing_device_name\030\007 \001(\t\022\032\n\022original_mime_t" - + "ype\030\010 \001(\t\022\031\n\robfuscated_id\030\t \001(\003B\002\030\001\022\023\n\013" - + "audio_topic\030\n \001(\t\"\305\001\n\017InteractionType\022 \n" - + "\034INTERACTION_TYPE_UNSPECIFIED\020\000\022\016\n\nDISCU" - + "SSION\020\001\022\020\n\014PRESENTATION\020\002\022\016\n\nPHONE_CALL\020" - + "\003\022\r\n\tVOICEMAIL\020\004\022\033\n\027PROFESSIONALLY_PRODU" - + "CED\020\005\022\020\n\014VOICE_SEARCH\020\006\022\021\n\rVOICE_COMMAND" - + "\020\007\022\r\n\tDICTATION\020\010\"d\n\022MicrophoneDistance\022" - + "#\n\037MICROPHONE_DISTANCE_UNSPECIFIED\020\000\022\r\n\t" - + "NEARFIELD\020\001\022\014\n\010MIDFIELD\020\002\022\014\n\010FARFIELD\020\003\"" - + "N\n\021OriginalMediaType\022#\n\037ORIGINAL_MEDIA_T" - + "YPE_UNSPECIFIED\020\000\022\t\n\005AUDIO\020\001\022\t\n\005VIDEO\020\002\"" - + "\244\001\n\023RecordingDeviceType\022%\n!RECORDING_DEV" - + "ICE_TYPE_UNSPECIFIED\020\000\022\016\n\nSMARTPHONE\020\001\022\006" - + "\n\002PC\020\002\022\016\n\nPHONE_LINE\020\003\022\013\n\007VEHICLE\020\004\022\030\n\024O" - + "THER_OUTDOOR_DEVICE\020\005\022\027\n\023OTHER_INDOOR_DE" - + "VICE\020\006\"/\n\rSpeechContext\022\017\n\007phrases\030\001 \003(\t" - + "\022\r\n\005boost\030\004 \001(\002\"D\n\020RecognitionAudio\022\021\n\007c" - + "ontent\030\001 \001(\014H\000\022\r\n\003uri\030\002 \001(\tH\000B\016\n\014audio_s" - + "ource\"\\\n\021RecognizeResponse\022G\n\007results\030\002 " - + "\003(\01326.google.cloud.speech.v1p1beta1.Spee" - + "chRecognitionResult\"\337\001\n\034LongRunningRecog" - + "nizeResponse\022G\n\007results\030\002 \003(\01326.google.c" - + "loud.speech.v1p1beta1.SpeechRecognitionR" - + "esult\022L\n\routput_config\030\006 \001(\01325.google.cl" - + "oud.speech.v1p1beta1.TranscriptOutputCon" - + "fig\022(\n\014output_error\030\007 \001(\0132\022.google.rpc.S" - + "tatus\"\203\002\n\034LongRunningRecognizeMetadata\022\030" - + "\n\020progress_percent\030\001 \001(\005\022.\n\nstart_time\030\002" - + " \001(\0132\032.google.protobuf.Timestamp\0224\n\020last" - + "_update_time\030\003 \001(\0132\032.google.protobuf.Tim" - + "estamp\022\020\n\003uri\030\004 \001(\tB\003\340A\003\022Q\n\routput_confi" - + "g\030\005 \001(\01325.google.cloud.speech.v1p1beta1." - + "TranscriptOutputConfigB\003\340A\003\"\277\002\n\032Streamin" - + "gRecognizeResponse\022!\n\005error\030\001 \001(\0132\022.goog" - + "le.rpc.Status\022J\n\007results\030\002 \003(\01329.google." - + "cloud.speech.v1p1beta1.StreamingRecognit" - + "ionResult\022d\n\021speech_event_type\030\004 \001(\0162I.g" + + "nMetadata.InteractionType\022$\n\034industry_na" + + "ics_code_of_audio\030\003 \001(\r\022b\n\023microphone_di" + + "stance\030\004 \001(\0162E.google.cloud.speech.v1p1b" + + "eta1.RecognitionMetadata.MicrophoneDista" + + "nce\022a\n\023original_media_type\030\005 \001(\0162D.googl" + + "e.cloud.speech.v1p1beta1.RecognitionMeta" + + "data.OriginalMediaType\022e\n\025recording_devi" + + "ce_type\030\006 \001(\0162F.google.cloud.speech.v1p1" + + "beta1.RecognitionMetadata.RecordingDevic" + + "eType\022\035\n\025recording_device_name\030\007 \001(\t\022\032\n\022" + + "original_mime_type\030\010 \001(\t\022\031\n\robfuscated_i" + + "d\030\t \001(\003B\002\030\001\022\023\n\013audio_topic\030\n \001(\t\"\305\001\n\017Int" + + "eractionType\022 \n\034INTERACTION_TYPE_UNSPECI" + + "FIED\020\000\022\016\n\nDISCUSSION\020\001\022\020\n\014PRESENTATION\020\002" + + "\022\016\n\nPHONE_CALL\020\003\022\r\n\tVOICEMAIL\020\004\022\033\n\027PROFE" + + "SSIONALLY_PRODUCED\020\005\022\020\n\014VOICE_SEARCH\020\006\022\021" + + "\n\rVOICE_COMMAND\020\007\022\r\n\tDICTATION\020\010\"d\n\022Micr" + + "ophoneDistance\022#\n\037MICROPHONE_DISTANCE_UN" + + "SPECIFIED\020\000\022\r\n\tNEARFIELD\020\001\022\014\n\010MIDFIELD\020\002" + + "\022\014\n\010FARFIELD\020\003\"N\n\021OriginalMediaType\022#\n\037O" + + "RIGINAL_MEDIA_TYPE_UNSPECIFIED\020\000\022\t\n\005AUDI" + + "O\020\001\022\t\n\005VIDEO\020\002\"\244\001\n\023RecordingDeviceType\022%" + + "\n!RECORDING_DEVICE_TYPE_UNSPECIFIED\020\000\022\016\n" + + "\nSMARTPHONE\020\001\022\006\n\002PC\020\002\022\016\n\nPHONE_LINE\020\003\022\013\n" + + "\007VEHICLE\020\004\022\030\n\024OTHER_OUTDOOR_DEVICE\020\005\022\027\n\023" + + "OTHER_INDOOR_DEVICE\020\006\"/\n\rSpeechContext\022\017" + + "\n\007phrases\030\001 \003(\t\022\r\n\005boost\030\004 \001(\002\"D\n\020Recogn" + + "itionAudio\022\021\n\007content\030\001 \001(\014H\000\022\r\n\003uri\030\002 \001" + + "(\tH\000B\016\n\014audio_source\"\\\n\021RecognizeRespons" + + "e\022G\n\007results\030\002 \003(\01326.google.cloud.speech" + + ".v1p1beta1.SpeechRecognitionResult\"\337\001\n\034L" + + "ongRunningRecognizeResponse\022G\n\007results\030\002" + + " \003(\01326.google.cloud.speech.v1p1beta1.Spe" + + "echRecognitionResult\022L\n\routput_config\030\006 " + + "\001(\01325.google.cloud.speech.v1p1beta1.Tran" + + "scriptOutputConfig\022(\n\014output_error\030\007 \001(\013" + + "2\022.google.rpc.Status\"\203\002\n\034LongRunningReco" + + "gnizeMetadata\022\030\n\020progress_percent\030\001 \001(\005\022" + + ".\n\nstart_time\030\002 \001(\0132\032.google.protobuf.Ti" + + "mestamp\0224\n\020last_update_time\030\003 \001(\0132\032.goog" + + "le.protobuf.Timestamp\022\020\n\003uri\030\004 \001(\tB\003\340A\003\022" + + "Q\n\routput_config\030\005 \001(\01325.google.cloud.sp" + + "eech.v1p1beta1.TranscriptOutputConfigB\003\340" + + "A\003\"\277\002\n\032StreamingRecognizeResponse\022!\n\005err" + + "or\030\001 \001(\0132\022.google.rpc.Status\022J\n\007results\030" + + "\002 \003(\01329.google.cloud.speech.v1p1beta1.St" + + "reamingRecognitionResult\022d\n\021speech_event" + + "_type\030\004 \001(\0162I.google.cloud.speech.v1p1be" + + "ta1.StreamingRecognizeResponse.SpeechEve" + + "ntType\"L\n\017SpeechEventType\022\034\n\030SPEECH_EVEN" + + "T_UNSPECIFIED\020\000\022\033\n\027END_OF_SINGLE_UTTERAN" + + "CE\020\001\"\371\001\n\032StreamingRecognitionResult\022Q\n\014a" + + "lternatives\030\001 \003(\0132;.google.cloud.speech." + + "v1p1beta1.SpeechRecognitionAlternative\022\020" + + "\n\010is_final\030\002 \001(\010\022\021\n\tstability\030\003 \001(\002\0222\n\017r" + + "esult_end_time\030\004 \001(\0132\031.google.protobuf.D" + + "uration\022\023\n\013channel_tag\030\005 \001(\005\022\032\n\rlanguage" + + "_code\030\006 \001(\tB\003\340A\003\"\235\001\n\027SpeechRecognitionRe" + + "sult\022Q\n\014alternatives\030\001 \003(\0132;.google.clou" + + "d.speech.v1p1beta1.SpeechRecognitionAlte" + + "rnative\022\023\n\013channel_tag\030\002 \001(\005\022\032\n\rlanguage" + + "_code\030\005 \001(\tB\003\340A\003\"~\n\034SpeechRecognitionAlt" + + "ernative\022\022\n\ntranscript\030\001 \001(\t\022\022\n\nconfiden" + + "ce\030\002 \001(\002\0226\n\005words\030\003 \003(\0132\'.google.cloud.s" + + "peech.v1p1beta1.WordInfo\"\242\001\n\010WordInfo\022-\n" + + "\nstart_time\030\001 \001(\0132\031.google.protobuf.Dura" + + "tion\022+\n\010end_time\030\002 \001(\0132\031.google.protobuf" + + ".Duration\022\014\n\004word\030\003 \001(\t\022\022\n\nconfidence\030\004 " + + "\001(\002\022\030\n\013speaker_tag\030\005 \001(\005B\003\340A\0032\202\005\n\006Speech" + + "\022\245\001\n\tRecognize\022/.google.cloud.speech.v1p" + + "1beta1.RecognizeRequest\0320.google.cloud.s" + + "peech.v1p1beta1.RecognizeResponse\"5\202\323\344\223\002" + + " \"\033/v1p1beta1/speech:recognize:\001*\332A\014conf" + + "ig,audio\022\362\001\n\024LongRunningRecognize\022:.goog" + + "le.cloud.speech.v1p1beta1.LongRunningRec" + + "ognizeRequest\032\035.google.longrunning.Opera" + + "tion\"\177\202\323\344\223\002+\"&/v1p1beta1/speech:longrunn" + + "ingrecognize:\001*\332A\014config,audio\312A<\n\034LongR" + + "unningRecognizeResponse\022\034LongRunningReco" + + "gnizeMetadata\022\217\001\n\022StreamingRecognize\0228.g" + "oogle.cloud.speech.v1p1beta1.StreamingRe" - + "cognizeResponse.SpeechEventType\"L\n\017Speec" - + "hEventType\022\034\n\030SPEECH_EVENT_UNSPECIFIED\020\000" - + "\022\033\n\027END_OF_SINGLE_UTTERANCE\020\001\"\371\001\n\032Stream" - + "ingRecognitionResult\022Q\n\014alternatives\030\001 \003" - + "(\0132;.google.cloud.speech.v1p1beta1.Speec" - + "hRecognitionAlternative\022\020\n\010is_final\030\002 \001(" - + "\010\022\021\n\tstability\030\003 \001(\002\0222\n\017result_end_time\030" - + "\004 \001(\0132\031.google.protobuf.Duration\022\023\n\013chan" - + "nel_tag\030\005 \001(\005\022\032\n\rlanguage_code\030\006 \001(\tB\003\340A" - + "\003\"\235\001\n\027SpeechRecognitionResult\022Q\n\014alterna" - + "tives\030\001 \003(\0132;.google.cloud.speech.v1p1be" - + "ta1.SpeechRecognitionAlternative\022\023\n\013chan" - + "nel_tag\030\002 \001(\005\022\032\n\rlanguage_code\030\005 \001(\tB\003\340A" - + "\003\"~\n\034SpeechRecognitionAlternative\022\022\n\ntra" - + "nscript\030\001 \001(\t\022\022\n\nconfidence\030\002 \001(\002\0226\n\005wor" - + "ds\030\003 \003(\0132\'.google.cloud.speech.v1p1beta1" - + ".WordInfo\"\242\001\n\010WordInfo\022-\n\nstart_time\030\001 \001" - + "(\0132\031.google.protobuf.Duration\022+\n\010end_tim" - + "e\030\002 \001(\0132\031.google.protobuf.Duration\022\014\n\004wo" - + "rd\030\003 \001(\t\022\022\n\nconfidence\030\004 \001(\002\022\030\n\013speaker_" - + "tag\030\005 \001(\005B\003\340A\0032\202\005\n\006Speech\022\245\001\n\tRecognize\022" - + "/.google.cloud.speech.v1p1beta1.Recogniz" - + "eRequest\0320.google.cloud.speech.v1p1beta1" - + ".RecognizeResponse\"5\202\323\344\223\002 \"\033/v1p1beta1/s" - + "peech:recognize:\001*\332A\014config,audio\022\362\001\n\024Lo" - + "ngRunningRecognize\022:.google.cloud.speech" - + ".v1p1beta1.LongRunningRecognizeRequest\032\035" - + ".google.longrunning.Operation\"\177\202\323\344\223\002+\"&/" - + "v1p1beta1/speech:longrunningrecognize:\001*" - + "\332A\014config,audio\312A<\n\034LongRunningRecognize" - + "Response\022\034LongRunningRecognizeMetadata\022\217" - + "\001\n\022StreamingRecognize\0228.google.cloud.spe" - + "ech.v1p1beta1.StreamingRecognizeRequest\032" - + "9.google.cloud.speech.v1p1beta1.Streamin" - + "gRecognizeResponse\"\000(\0010\001\032I\312A\025speech.goog" - + "leapis.com\322A.https://www.googleapis.com/" - + "auth/cloud-platformB\200\001\n!com.google.cloud" - + ".speech.v1p1beta1B\013SpeechProtoP\001ZCgoogle" - + ".golang.org/genproto/googleapis/cloud/sp" - + "eech/v1p1beta1;speech\370\001\001\242\002\003GCSb\006proto3" + + "cognizeRequest\0329.google.cloud.speech.v1p" + + "1beta1.StreamingRecognizeResponse\"\000(\0010\001\032" + + "I\312A\025speech.googleapis.com\322A.https://www." + + "googleapis.com/auth/cloud-platformB\200\001\n!c" + + "om.google.cloud.speech.v1p1beta1B\013Speech" + + "ProtoP\001ZCgoogle.golang.org/genproto/goog" + + "leapis/cloud/speech/v1p1beta1;speech\370\001\001\242" + + "\002\003GCSb\006proto3" }; descriptor = com.google.protobuf.Descriptors.FileDescriptor.internalBuildGeneratedFileFrom( diff --git a/proto-google-cloud-speech-v1p1beta1/src/main/proto/google/cloud/speech/v1p1beta1/cloud_speech.proto b/proto-google-cloud-speech-v1p1beta1/src/main/proto/google/cloud/speech/v1p1beta1/cloud_speech.proto index cf183d012..1deb3c7cf 100644 --- a/proto-google-cloud-speech-v1p1beta1/src/main/proto/google/cloud/speech/v1p1beta1/cloud_speech.proto +++ b/proto-google-cloud-speech-v1p1beta1/src/main/proto/google/cloud/speech/v1p1beta1/cloud_speech.proto @@ -1,4 +1,3 @@ - // Copyright 2021 Google LLC // // Licensed under the Apache License, Version 2.0 (the "License"); @@ -244,6 +243,12 @@ message RecognitionConfig { // 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)). This is a Beta features and + // only available in v1p1beta1. `sample_rate_hertz` must be one of 8000, + // 12000, 16000, 24000, or 48000. + WEBM_OPUS = 9; } // Encoding of audio data sent in all `RecognitionAudio` messages. @@ -406,7 +411,7 @@ message RecognitionConfig { // // // video - // Best for audio that originated from from video or includes multiple + // 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. diff --git a/synth.metadata b/synth.metadata index 2c754a4d9..84e1e5825 100644 --- a/synth.metadata +++ b/synth.metadata @@ -4,23 +4,23 @@ "git": { "name": ".", "remote": "https://github.com/googleapis/java-speech.git", - "sha": "c812cb7783186186061f01fa65c752162df8dc81" + "sha": "4530ef98a4d5dbe9def59fdd26c6e2ee37041763" } }, { "git": { "name": "googleapis", "remote": "https://github.com/googleapis/googleapis.git", - "sha": "93b078ae0decd51e618041bb337a8d592d0c998b", - "internalRef": "367239272" + "sha": "36a84fe3eaf841f56c4b6683d1c0403f7b503092", + "internalRef": "370523741" } }, { "git": { "name": "googleapis", "remote": "https://github.com/googleapis/googleapis.git", - "sha": "93b078ae0decd51e618041bb337a8d592d0c998b", - "internalRef": "367239272" + "sha": "36a84fe3eaf841f56c4b6683d1c0403f7b503092", + "internalRef": "370523741" } }, {