suguo
/
googleapis
0
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Add speech adaptation, phrase sets and custom classes. 

PiperOrigin-RevId: 306280989
This commit is contained in:
Google APIs 2020-04-13 12:05:23 -07:00 committed by Copybara-Service
parent 3824f547aa
commit 4d61e1cb40
3 changed files with 179 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
google/cloud/speech/v1p1beta1/BUILD.bazel
View File

@ -13,11 +13,13 @@ proto_library(
name = "speech_proto",
srcs = [
"cloud_speech.proto",
"resource.proto",
],
deps = [
"//google/api:annotations_proto",
"//google/api:client_proto",
"//google/api:field_behavior_proto",
"//google/api:resource_proto",
"//google/longrunning:operations_proto",
"//google/rpc:status_proto",
"@com_google_protobuf//:any_proto",
@ -166,6 +168,7 @@ moved_proto_library(
"//google/api:annotations_proto",
"//google/api:client_proto",
"//google/api:field_behavior_proto",
"//google/api:resource_proto",
"//google/longrunning:operations_proto",
"//google/rpc:status_proto",
"@com_google_protobuf//:any_proto",

75
google/cloud/speech/v1p1beta1/cloud_speech.proto
View File

@ -1,4 +1,4 @@
// Copyright 2019 Google LLC.
// Copyright 2020 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
@ -11,7 +11,6 @@
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
syntax = "proto3";
@ -20,6 +19,8 @@ package google.cloud.speech.v1p1beta1;
import "google/api/annotations.proto";
import "google/api/client.proto";
import "google/api/field_behavior.proto";
import "google/api/resource.proto";
import "google/cloud/speech/v1p1beta1/resource.proto";
import "google/longrunning/operations.proto";
import "google/protobuf/any.proto";
import "google/protobuf/duration.proto";
@ -36,7 +37,8 @@ option objc_class_prefix = "GCS";
// Service that implements Google Cloud Speech API.
service Speech {
option (google.api.default_host) = "speech.googleapis.com";
option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform";
option (google.api.oauth_scopes) =
"https://www.googleapis.com/auth/cloud-platform";
// Performs synchronous speech recognition: receive results after all audio
// has been sent and processed.
@ -54,7 +56,8 @@ service Speech {
// a `LongRunningRecognizeResponse` message.
// For more information on asynchronous speech recognition, see the
// [how-to](https://cloud.google.com/speech-to-text/docs/async-recognize).
rpc LongRunningRecognize(LongRunningRecognizeRequest) returns (google.longrunning.Operation) {
rpc LongRunningRecognize(LongRunningRecognizeRequest)
returns (google.longrunning.Operation) {
option (google.api.http) = {
post: "/v1p1beta1/speech:longrunningrecognize"
body: "*"
@ -68,8 +71,8 @@ service Speech {
// Performs bidirectional streaming speech recognition: receive results while
// sending audio. This method is only available via the gRPC API (not REST).
rpc StreamingRecognize(stream StreamingRecognizeRequest) returns (stream StreamingRecognizeResponse) {
}
rpc StreamingRecognize(stream StreamingRecognizeRequest)
returns (stream StreamingRecognizeResponse) {}
}
// The top-level message sent by the client for the `Recognize` method.
@ -169,7 +172,8 @@ message RecognitionConfig {
// 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.
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
// code.
enum AudioEncoding {
// Not specified.
ENCODING_UNSPECIFIED = 0;
@ -215,14 +219,15 @@ message RecognitionConfig {
SPEEX_WITH_HEADER_BYTE = 7;
// MP3 audio. Support all standard MP3 bitrates (which range from 32-320
// kbps). When using this encoding, `sample_rate_hertz` can be optionally
// unset if not known.
// kbps). When using this encoding, `sample_rate_hertz` has to match the
// sample rate of the file being used.
MP3 = 8;
}
// 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.v1p1beta1.RecognitionConfig.AudioEncoding].
AudioEncoding encoding = 1;
// Sample rate in Hertz of the audio data sent in all
@ -231,7 +236,8 @@ 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, but is
// required for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding].
// required for all other audio formats. For details, see
// [AudioEncoding][google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding].
int32 sample_rate_hertz = 2;
// The number of channels in the input audio data.
@ -289,6 +295,13 @@ message RecognitionConfig {
// won't be filtered out.
bool profanity_filter = 5;
// Speech adaptation configuration improves the accuracy of speech
// recognition. When speech adaptation is set it supersedes the
// `speech_contexts` field. For more information, see the [speech
// adaptation](https://cloud.google.com/speech-to-text/docs/context-strength)
// documentation.
SpeechAdaptation adaptation = 20;
// Array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
// A means to provide context to assist the speech recognition. For more
// information, see
@ -311,9 +324,6 @@ message RecognitionConfig {
// 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.
// Note: This is currently offered as an experimental service, complimentary
// to all users. In the future this may be exclusively available as a
// premium feature.
bool enable_automatic_punctuation = 11;
// If 'true', enables speaker detection for each recognized word in
@ -401,6 +411,10 @@ message SpeakerDiarizationConfig {
// flexibility by allowing the system to automatically determine the correct
// number of speakers. If not set, the default value is 6.
int32 max_speaker_count = 3;
// Output only. Unused.
int32 speaker_tag = 5
[deprecated = true, (google.api.field_behavior) = OUTPUT_ONLY];
}
// Description of audio data to be recognized.
@ -564,8 +578,8 @@ message SpeechContext {
// 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).
// returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
// See [content limits](https://cloud.google.com/speech-to-text/quotas#content).
message RecognitionAudio {
// The audio source, which is either inline content or a Google Cloud
// Storage uri.
@ -580,8 +594,9 @@ message RecognitionAudio {
// 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).
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
// For more information, see [Request
// URIs](https://cloud.google.com/storage/docs/reference-uris).
string uri = 2;
}
}
@ -619,6 +634,10 @@ message LongRunningRecognizeMetadata {
// Time of the most recent processing update.
google.protobuf.Timestamp last_update_time = 3;
// The URI of the audio file being transcribed. Empty if the audio was sent
// as byte content.
string uri = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// `StreamingRecognizeResponse` is the only message returned to the client by
@ -732,10 +751,10 @@ message StreamingRecognitionResult {
// For audio_channel_count = N, its output values can range from '1' to 'N'.
int32 channel_tag = 5;
// 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;
// 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 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// A speech recognition result corresponding to a portion of the audio.
@ -751,10 +770,10 @@ message SpeechRecognitionResult {
// For audio_channel_count = N, its output values can range from '1' to 'N'.
int32 channel_tag = 2;
// 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;
// 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 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// Alternative hypotheses (a.k.a. n-best list).
@ -807,10 +826,10 @@ message WordInfo {
// The default of 0.0 is a sentinel value indicating `confidence` was not set.
float confidence = 4;
// A distinct integer value is assigned for every speaker within
// 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;
int32 speaker_tag = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
}

129
google/cloud/speech/v1p1beta1/resource.proto Normal file
View File

@ -0,0 +1,129 @@
// Copyright 2020 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
syntax = "proto3";
package google.cloud.speech.v1p1beta1;
import "google/api/annotations.proto";
import "google/api/resource.proto";
option cc_enable_arenas = true;
option go_package = "google.golang.org/genproto/googleapis/cloud/speech/v1p1beta1;speech";
option java_multiple_files = true;
option java_outer_classname = "SpeechResourceProto";
option java_package = "com.google.cloud.speech.v1p1beta1";
option objc_class_prefix = "GCS";
// 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.
message CustomClass {
option (google.api.resource) = {
type: "speech.googleapis.com/CustomClass"
pattern: "projects/{project}/locations/{location}/customClasses/{custom_class}"
};
// An item of the class.
message ClassItem {
// The class item's value.
string value = 1;
}
// The resource name of the custom class.
string name = 1;
// If this custom class is a resource, the custom_class_id is the resource id
// of the CustomClass.
string custom_class_id = 2;
// A collection of class items.
repeated ClassItem items = 3;
}
// Provides "hints" to the speech recognizer to favor specific words and phrases
// in the results.
message PhraseSet {
option (google.api.resource) = {
type: "speech.googleapis.com/PhraseSet"
pattern: "projects/{project}/locations/{location}/phraseSets/{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}`).
message Phrase {
// The phrase itself.
string value = 1;
// 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 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. Speech recognition
// will skip PhraseSets with a boost value of 0.
float boost = 2;
}
// The resource name of the phrase set.
string name = 1;
// A list of word and phrases.
repeated Phrase phrases = 2;
// 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. Speech recognition
// will skip PhraseSets with a boost value of 0.
float boost = 4;
}
// Speech adaptation configuration.
message 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.
repeated PhraseSet phrase_sets = 1;
// 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`.
repeated CustomClass custom_classes = 2;
}