Skip to content

Commit

Permalink
[CHANGE ME] Re-generated speech to pick up changes in the API or clie…
Browse files Browse the repository at this point in the history 
…nt library generator.
  • Loading branch information
@yoshi-automation
yoshi-automation committed Feb 1, 2019
1 parent 15567b3 commit d4221e2
Show file tree
Hide file tree
Showing 4 changed files with 12 additions and 216 deletions.
220 changes: 9 additions & 211 deletions speech/google/cloud/speech_v1/proto/cloud_speech.proto
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@

syntax = "proto3";

package google.cloud.speech.v1p1beta1;
package google.cloud.speech.v1;

import "google/api/annotations.proto";
import "google/longrunning/operations.proto";
Expand All @@ -26,10 +26,10 @@ import "google/protobuf/timestamp.proto";
import "google/rpc/status.proto";

option cc_enable_arenas = true;
option go_package = "google.golang.org/genproto/googleapis/cloud/speech/v1p1beta1;speech";
option go_package = "google.golang.org/genproto/googleapis/cloud/speech/v1;speech";
option java_multiple_files = true;
option java_outer_classname = "SpeechProto";
option java_package = "com.google.cloud.speech.v1p1beta1";
option java_package = "com.google.cloud.speech.v1";


// Service that implements Google Cloud Speech API.
Expand All @@ -38,7 +38,7 @@ service Speech {
// has been sent and processed.
rpc Recognize(RecognizeRequest) returns (RecognizeResponse) {
option (google.api.http) = {
post: "/v1p1beta1/speech:recognize"
post: "/v1/speech:recognize"
body: "*"
};
}
Expand All @@ -49,7 +49,7 @@ service Speech {
// a `LongRunningRecognizeResponse` message.
rpc LongRunningRecognize(LongRunningRecognizeRequest) returns (google.longrunning.Operation) {
option (google.api.http) = {
post: "/v1p1beta1/speech:longrunningrecognize"
post: "/v1/speech:longrunningrecognize"
body: "*"
};
}
Expand Down Expand Up @@ -203,7 +203,7 @@ message 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.v1p1beta1.RecognitionConfig.AudioEncoding].
// for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
AudioEncoding encoding = 1;

// Sample rate in Hertz of the audio data sent in all
Expand All @@ -212,7 +212,7 @@ message RecognitionConfig {
// 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 and required
// for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding].
// for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
int32 sample_rate_hertz = 2;

// *Optional* The number of channels in the input audio data.
Expand All @@ -226,7 +226,7 @@ message RecognitionConfig {
// `enable_separate_recognition_per_channel` to 'true'.
int32 audio_channel_count = 7;

// This needs to be set to ‘true’ explicitly and `audio_channel_count` > 1
// 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
Expand All @@ -241,20 +241,6 @@ message RecognitionConfig {
// for a list of the currently supported language codes.
string language_code = 3;

// *Optional* 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](/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).
repeated string alternative_language_codes = 18;

// *Optional* Maximum number of recognition hypotheses to be returned.
// Specifically, the maximum number of `SpeechRecognitionAlternative` messages
// within each `SpeechRecognitionResult`.
Expand All @@ -269,7 +255,7 @@ message RecognitionConfig {
// won't be filtered out.
bool profanity_filter = 5;

// *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
// *Optional* array of [SpeechContext][google.cloud.speech.v1.SpeechContext].
// A means to provide context to assist the speech recognition. For more
// information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
repeated SpeechContext speech_contexts = 6;
Expand All @@ -280,11 +266,6 @@ message RecognitionConfig {
// `false`.
bool enable_word_time_offsets = 8;

// *Optional* 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`.
bool enable_word_confidence = 15;

// *Optional* 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.
Expand All @@ -294,26 +275,6 @@ message RecognitionConfig {
// premium feature.
bool enable_automatic_punctuation = 11;

// *Optional* If 'true', enables speaker detection for each recognized word in
// the top alternative of the recognition result using a speaker_tag provided
// in the WordInfo.
// Note: When this is true, 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.
bool enable_speaker_diarization = 16;

// *Optional*
// If set, specifies the estimated number of speakers in the conversation.
// If not set, defaults to '2'.
// Ignored unless enable_speaker_diarization is set to true."
int32 diarization_speaker_count = 17;

// *Optional* Metadata regarding this request.
RecognitionMetadata metadata = 9;

// *Optional* 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
Expand Down Expand Up @@ -366,137 +327,6 @@ message RecognitionConfig {
bool use_enhanced = 14;
}

// Description of audio data to be recognized.
message RecognitionMetadata {
// Use case categories that the audio recognition request can be described
// by.
enum InteractionType {
// Use case is either unknown or is something other than one of the other
// values below.
INTERACTION_TYPE_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.
PHONE_CALL = 3;

// A recorded message intended for another person to listen to.
VOICEMAIL = 4;

// Professionally produced audio (eg. TV Show, Podcast).
PROFESSIONALLY_PRODUCED = 5;

// Transcribe spoken questions and queries into text.
VOICE_SEARCH = 6;

// Transcribe voice commands, such as for controlling a device.
VOICE_COMMAND = 7;

// Transcribe speech to text to create a written document, such as a
// text-message, email or report.
DICTATION = 8;
}

// Enumerates the types of capture settings describing an audio file.
enum MicrophoneDistance {
// Audio type is not known.
MICROPHONE_DISTANCE_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;
}

// The original media the speech was recorded on.
enum OriginalMediaType {
// Unknown original media type.
ORIGINAL_MEDIA_TYPE_UNSPECIFIED = 0;

// The speech data is an audio recording.
AUDIO = 1;

// The speech data originally recorded on a video.
VIDEO = 2;
}

// The type of device the speech was recorded with.
enum RecordingDeviceType {
// The recording device is unknown.
RECORDING_DEVICE_TYPE_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.
PHONE_LINE = 3;

// Speech was recorded in a vehicle.
VEHICLE = 4;

// Speech was recorded outdoors.
OTHER_OUTDOOR_DEVICE = 5;

// Speech was recorded indoors.
OTHER_INDOOR_DEVICE = 6;
}

// The use case most closely describing the audio content to be recognized.
InteractionType interaction_type = 1;

// 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/.
uint32 industry_naics_code_of_audio = 3;

// The audio type that most closely describes the audio being recognized.
MicrophoneDistance microphone_distance = 4;

// The original media the speech was recorded on.
OriginalMediaType original_media_type = 5;

// The type of device the speech was recorded with.
RecordingDeviceType recording_device_type = 6;

// The device used to make the recording. Examples 'Nexus 5X' or
// 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
// 'Cardioid Microphone'.
string recording_device_name = 7;

// 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
string original_mime_type = 8;

// Obfuscated (privacy-protected) ID of the user, to identify number of
// unique users using the service.
int64 obfuscated_id = 9;

// Description of the content. Eg. "Recordings of federal supreme court
// hearings from 2012".
string audio_topic = 10;
}

// Provides "hints" to the speech recognizer to favor specific words and phrases
// in the results.
message SpeechContext {
Expand Down Expand Up @@ -670,20 +500,10 @@ message StreamingRecognitionResult {
// The default of 0.0 is a sentinel value indicating `stability` was not set.
float stability = 3;

// Output only. Time offset of the end of this result relative to the
// beginning of the audio.
google.protobuf.Duration result_end_time = 4;

// 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'.
int32 channel_tag = 5;

// 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.
string language_code = 6;
}

// A speech recognition result corresponding to a portion of the audio.
Expand All @@ -698,12 +518,6 @@ message SpeechRecognitionResult {
// recognized result for the audio from that channel.
// For audio_channel_count = N, its output values can range from '1' to 'N'.
int32 channel_tag = 2;

// 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.
string language_code = 5;
}

// Alternative hypotheses (a.k.a. n-best list).
Expand Down Expand Up @@ -746,20 +560,4 @@ message WordInfo {

// Output only. The word corresponding to this set of information.
string word = 3;

// Output only. 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.
float confidence = 4;

// 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 in the
// top alternative.
int32 speaker_tag = 5;
}
1 change: 0 additions & 1 deletion speech/google/cloud/speech_v1/proto/cloud_speech_pb2.py
View file

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 0 additions & 1 deletion speech/google/cloud/speech_v1p1beta1/proto/cloud_speech_pb2.py
View file

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

6 changes: 3 additions & 3 deletions speech/synth.metadata
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
{
"updateTime": "2019-01-31T00:53:35.360883Z",
"updateTime": "2019-02-01T01:10:29.243119Z",
"sources": [
{
"generator": {
Expand All @@ -12,8 +12,8 @@
"git": {
"name": "googleapis",
"remote": "https://github.com/googleapis/googleapis.git",
"sha": "9607c39973de36d319ec8861ac39a826163e21de",
"internalRef": "231680111"
"sha": "acb5253cd11cd43cab93eb153d6e48ba0fa5303d",
"internalRef": "231786007"
}
},
{
Expand Down

0 comments on commit d4221e2

Please sign in to comment.