com.google.cloud.speech.v1p1beta1.RecognitionConfigOrBuilder 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-v1p1beta1 Show documentation
Show all versions of proto-google-cloud-speech-v1p1beta1 Show documentation
PROTO library for proto-google-cloud-speech-v1p1beta1
// Generated by the protocol buffer compiler. DO NOT EDIT!
// source: google/cloud/speech/v1p1beta1/cloud_speech.proto
package com.google.cloud.speech.v1p1beta1;
public interface RecognitionConfigOrBuilder extends
// @@protoc_insertion_point(interface_extends:google.cloud.speech.v1p1beta1.RecognitionConfig)
com.google.protobuf.MessageOrBuilder {
/**
*
* 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].
*
*
* .google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding encoding = 1;
*/
int getEncodingValue();
/**
*
* 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].
*
*
* .google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding encoding = 1;
*/
com.google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding getEncoding();
/**
*
* Sample rate in Hertz of the audio data sent in all
* `RecognitionAudio` messages. Valid values are: 8000-48000.
* 16000 is optimal. For best results, set the sampling rate of the audio
* 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].
*
*
* int32 sample_rate_hertz = 2;
*/
int getSampleRateHertz();
/**
*
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
* See [Language Support](https://cloud.google.com/speech/docs/languages)
* for a list of the currently supported language codes.
*
*
* string language_code = 3;
*/
java.lang.String getLanguageCode();
/**
*
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
* See [Language Support](https://cloud.google.com/speech/docs/languages)
* for a list of the currently supported language codes.
*
*
* string language_code = 3;
*/
com.google.protobuf.ByteString
getLanguageCodeBytes();
/**
*
* *Optional* Maximum number of recognition hypotheses to be returned.
* Specifically, the maximum number of `SpeechRecognitionAlternative` messages
* within each `SpeechRecognitionResult`.
* The server may return fewer than `max_alternatives`.
* Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of
* one. If omitted, will return a maximum of one.
*
*
* int32 max_alternatives = 4;
*/
int getMaxAlternatives();
/**
*
* *Optional* If set to `true`, the server will attempt to filter out
* profanities, replacing all but the initial character in each filtered word
* with asterisks, e.g. "f***". If set to `false` or omitted, profanities
* won't be filtered out.
*
*
* bool profanity_filter = 5;
*/
boolean getProfanityFilter();
/**
*
* *Optional* A means to provide context to assist the speech recognition.
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
*/
java.util.List
getSpeechContextsList();
/**
*
* *Optional* A means to provide context to assist the speech recognition.
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
*/
com.google.cloud.speech.v1p1beta1.SpeechContext getSpeechContexts(int index);
/**
*
* *Optional* A means to provide context to assist the speech recognition.
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
*/
int getSpeechContextsCount();
/**
*
* *Optional* A means to provide context to assist the speech recognition.
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
*/
java.util.List
getSpeechContextsOrBuilderList();
/**
*
* *Optional* A means to provide context to assist the speech recognition.
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
*/
com.google.cloud.speech.v1p1beta1.SpeechContextOrBuilder getSpeechContextsOrBuilder(
int index);
/**
*
* *Optional* If `true`, the top result includes a list of words and
* the start and end time offsets (timestamps) for those words. If
* `false`, no word-level time offset information is returned. The default is
* `false`.
*
*
* bool enable_word_time_offsets = 8;
*/
boolean getEnableWordTimeOffsets();
/**
*
* *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.
* 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;
*/
boolean getEnableAutomaticPunctuation();
/**
*
* *Optional* Metadata regarding this request.
*
*
* .google.cloud.speech.v1p1beta1.RecognitionMetadata metadata = 9;
*/
boolean hasMetadata();
/**
*
* *Optional* Metadata regarding this request.
*
*
* .google.cloud.speech.v1p1beta1.RecognitionMetadata metadata = 9;
*/
com.google.cloud.speech.v1p1beta1.RecognitionMetadata getMetadata();
/**
*
* *Optional* Metadata regarding this request.
*
*
* .google.cloud.speech.v1p1beta1.RecognitionMetadata metadata = 9;
*/
com.google.cloud.speech.v1p1beta1.RecognitionMetadataOrBuilder getMetadataOrBuilder();
/**
*
* *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
* in the RecognitionConfig.
* <table>
* <tr>
* <td><b>Model</b></td>
* <td><b>Description</b></td>
* </tr>
* <tr>
* <td><code>command_and_search</code></td>
* <td>Best for short queries such as voice commands or voice search.</td>
* </tr>
* <tr>
* <td><code>phone_call</code></td>
* <td>Best for audio that originated from a phone call (typically
* recorded at an 8khz sampling rate).</td>
* </tr>
* <tr>
* <td><code>video</code></td>
* <td>Best for audio that originated from 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>
* </tr>
* <tr>
* <td><code>default</code></td>
* <td>Best for audio that is not one of the specific audio models.
* For example, long-form audio. Ideally the audio is high-fidelity,
* recorded at a 16khz or greater sampling rate.</td>
* </tr>
* </table>
*
*
* string model = 13;
*/
java.lang.String getModel();
/**
*
* *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
* in the RecognitionConfig.
* <table>
* <tr>
* <td><b>Model</b></td>
* <td><b>Description</b></td>
* </tr>
* <tr>
* <td><code>command_and_search</code></td>
* <td>Best for short queries such as voice commands or voice search.</td>
* </tr>
* <tr>
* <td><code>phone_call</code></td>
* <td>Best for audio that originated from a phone call (typically
* recorded at an 8khz sampling rate).</td>
* </tr>
* <tr>
* <td><code>video</code></td>
* <td>Best for audio that originated from 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>
* </tr>
* <tr>
* <td><code>default</code></td>
* <td>Best for audio that is not one of the specific audio models.
* For example, long-form audio. Ideally the audio is high-fidelity,
* recorded at a 16khz or greater sampling rate.</td>
* </tr>
* </table>
*
*
* string model = 13;
*/
com.google.protobuf.ByteString
getModelBytes();
/**
*
* *Optional* Set to true to use an enhanced model for speech recognition.
* You must also set the `model` field to a valid, enhanced model. If
* `use_enhanced` is set to true and the `model` field is not set, then
* `use_enhanced` is ignored. If `use_enhanced` is true and an enhanced
* version of the specified model does not exist, then the speech is
* recognized using the standard version of the specified model.
* Enhanced speech models require that you opt-in to the audio logging using
* instructions in the [alpha documentation](/speech/data-sharing). If you set
* `use_enhanced` to true and you have not enabled audio logging, then you
* will receive an error.
*
*
* bool use_enhanced = 14;
*/
boolean getUseEnhanced();
}