google.cloud.speech.v1.resource.proto Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of proto-google-cloud-speech-v1 Show documentation
Show all versions of proto-google-cloud-speech-v1 Show documentation
PROTO library for proto-google-cloud-speech-v1
// Copyright 2024 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.v1;
import "google/api/resource.proto";
option cc_enable_arenas = true;
option go_package = "cloud.google.com/go/speech/apiv1/speechpb;speechpb";
option java_multiple_files = true;
option java_outer_classname = "SpeechResourceProto";
option java_package = "com.google.cloud.speech.v1";
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. Case sensitive.
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}`).
//
// Speech-to-Text supports three locations: `global`, `us` (US North America),
// and `eu` (Europe). If you are calling the `speech.googleapis.com`
// endpoint, use the `global` location. To specify a region, use a
// [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints)
// with matching `us` or `eu` location value.
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 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 as well as adding
// phrases both with and without boost to your requests.
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 as well as adding
// phrases both with and without boost to your requests.
float boost = 4;
}
// Speech adaptation configuration.
message SpeechAdaptation {
message ABNFGrammar {
// All declarations and rules of an ABNF grammar broken up into multiple
// strings that will end up concatenated.
repeated string abnf_strings = 1;
}
// 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 phrase set resource names to use.
repeated string phrase_set_references = 2 [(google.api.resource_reference) = {
type: "speech.googleapis.com/PhraseSet"
}];
// 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 = 3;
// Augmented Backus-Naur form (ABNF) is a standardized grammar notation
// comprised by a set of derivation rules.
// See specifications: https://www.w3.org/TR/speech-grammar
ABNFGrammar abnf_grammar = 4;
}
// Transcription normalization configuration. Use transcription normalization
// to automatically replace parts of the transcript with phrases of your
// choosing. For StreamingRecognize, this normalization only applies to stable
// partial transcripts (stability > 0.8) and final transcripts.
message TranscriptNormalization {
// A single replacement configuration.
message Entry {
// What to replace. Max length is 100 characters.
string search = 1;
// What to replace with. Max length is 100 characters.
string replace = 2;
// Whether the search is case sensitive.
bool case_sensitive = 3;
}
// A list of replacement entries. We will perform replacement with one entry
// at a time. For example, the second entry in ["cat" => "dog", "mountain cat"
// => "mountain dog"] will never be applied because we will always process the
// first entry before it. At most 100 entries.
repeated Entry entries = 1;
}
© 2015 - 2024 Weber Informatics LLC | Privacy Policy