- //
- // | Model |
- // Description |
- //
- //
- // command_and_search |
- // Best for short queries such as voice commands or voice search. |
- //
- //
- // phone_call |
- // Best for audio that originated from a phone call (typically
- // recorded at an 8khz sampling rate). |
- //
- //
- // video |
- // 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. |
- //
- //
- // default |
- // 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. |
- //
- //
-
- // [*Optional*][*Unused*]
- string model = 13;
-
- // @exclude [*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 data logging using
- // instructions in the [documentation](/speech-to-text/enable-data-logging).
- // If you set `use_enhanced` to true and you have not enabled audio logging,
- // then you will receive an error.
-
- // [*Optional*][*Unused*]
- bool use_enhanced = 14;
-
- // [**Extension by Techmo**][*Optional*] Gender and age recognition parameters
- SpeechDurationConfig speech_duration_gender_recognition = 15;
-
- // [**Extension by Techmo**][*Optional*] Gender and age recognition parameters
- SpeechDurationConfig speech_duration_age_recognition = 16;
-}
-
-// [**Extension by Techmo**] Gender and age recognition parameters.
-message SpeechDurationConfig {
- // The way in which service decides when to start recognition.
- SpeechDurationThresholdMode speech_duration_threshold_mode = 3;
-
- // The minimum duration of speech in `audio` required to start recognition, in ms.
- // Ignored, unless `speech_duration_threshold_mode` is `CUSTOM`.
- uint32 speech_duration_threshold_ms = 4;
-}
-
-// [**Extension by Techmo**]
-// The possible ways for a service to decide when to start recognition
-// depending on a duration of speech in `audio`.
-enum SpeechDurationThresholdMode {
- // Use an implementation-defined threshold value carefully tuned to obtain best results.
- DEFAULT = 0;
-
- // Use an user-defined threshold value provided in the configuration message.
- CUSTOM = 1;
-
- // Disable early start of recognition and wait for the entire audio data.
- DISABLED = 2;
-}
-
-
-// @exclude Provides "hints" to the speech recognizer to favor specific words and phrases
-// in the results.
-
-message SpeechContext {
- // @exclude [*Optional*] Can be used to send a context phrase that switches the model
- // used during recognition. If the phrase correctly identifies the context model
- // used in service, it will be used instead of the general model for the current recognition.
- // Due to compatibility with Google API, the object is defined as a list of strings,
- // but only the first element of the list is used as the context phrase,
- // the rest are ignored if present.
-
- repeated string phrases = 1;
-}
-
-// [**Extension by Techmo**]
-// Provides a pair of configuration field name and value.
-message ConfigField {
- // Name of configuration field.
- string key = 1;
-
- // Value of configuration field.
- string value = 2;
-}
-
-// @exclude 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
-// [audio limits](https://cloud.google.com/speech/limits#content).
-
-// Contains audio data in the encoding specified in the `RecognitionConfig`.
-// Only `content` is allowed to be supplied.
-message RecognitionAudio {
-
- // @exclude The audio source, which is either inline content or a Google Cloud
- // Storage uri.
-
- // The audio source, which is inline content.
- oneof audio_source {
- // The audio data bytes encoded as specified in
- // `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
- // pure binary representation, whereas JSON representations use base64.
- bytes content = 1;
-
- // @exclude URI that points to a file that contains audio data bytes as specified in
- // `RecognitionConfig`. The file must not be compressed (for example, gzip).
- // 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).
-
- // [*Unsupported*]
- string uri = 2;
- }
-}
-
-// The only message returned to the client by the `Recognize` method. It
-// contains the result as zero or more sequential `SpeechRecognitionResult`
-// messages.
-message RecognizeResponse {
- // [*Output only*] Sequential list of transcription results corresponding to
- // sequential portions of audio.
- repeated SpeechRecognitionResult results = 2;
-}
-
-// // The only message returned to the client by the `LongRunningRecognize` method.
-// // It contains the result as zero or more sequential `SpeechRecognitionResult`
-// // messages. It is included in the `result.response` field of the `Operation`
-// // returned by the `GetOperation` call of the `google::longrunning::Operations`
-// // service.
-// message LongRunningRecognizeResponse {
-// // [*Output only*] Sequential list of transcription results corresponding to
-// // sequential portions of audio.
-// repeated SpeechRecognitionResult results = 2;
-// }
-
-// // Describes the progress of a long-running `LongRunningRecognize` call. It is
-// // included in the `metadata` field of the `Operation` returned by the
-// // `GetOperation` call of the `google::longrunning::Operations` service.
-// message LongRunningRecognizeMetadata {
-// // Approximate percentage of audio processed thus far. Guaranteed to be 100
-// // when the audio is fully processed and the results are available.
-// int32 progress_percent = 1;
-
-// // Time when the request was received.
-// google.protobuf.Timestamp start_time = 2;
-
-// // Time of the most recent processing update.
-// google.protobuf.Timestamp last_update_time = 3;
-// }
-
-// `StreamingRecognizeResponse` is the only message returned to the client by
-// `StreamingRecognize`. A series of one or more `StreamingRecognizeResponse`
-// messages are streamed back to the client.
-//
-// Here's an example of a series of ten `StreamingRecognizeResponse`s that might
-// be returned while processing audio:
-//
-// 1. results { alternatives { transcript: "tube" } stability: 0.01 }
-//
-// 2. results { alternatives { transcript: "to be a" } stability: 0.01 }
-//
-// 3. results { alternatives { transcript: "to be" } stability: 0.9 }
-// results { alternatives { transcript: " or not to be" } stability: 0.01 }
-//
-// 4. results { alternatives { transcript: "to be or not to be"
-// confidence: 0.92 }
-// alternatives { transcript: "to bee or not to bee" }
-// is_final: true }
-//
-// 5. results { alternatives { transcript: " that's" } stability: 0.01 }
-//
-// 6. results { alternatives { transcript: " that is" } stability: 0.9 }
-// results { alternatives { transcript: " the question" } stability: 0.01 }
-//
-// 7. results { alternatives { transcript: " that is the question"
-// confidence: 0.98 }
-// alternatives { transcript: " that was the question" }
-// is_final: true }
-//
-// Notes:
-//
-// - Only two of the above responses #4 and #7 contain final results; they are
-// indicated by `is_final: true`. Concatenating these together generates the
-// full transcript: "to be or not to be that is the question".
-//
-// - The others contain interim `results`. #3 and #6 contain two interim
-// `results`: the first portion has a high stability and is less likely to
-// change; the second portion has a low stability and is very likely to
-// change. A UI designer might choose to show only high stability `results`.
-//
-// - The specific `stability` and `confidence` values shown above are only for
-// illustrative purposes. Actual values may vary.
-//
-// - In each response, only one of these fields will be set:
-// `error`,
-// `speech_event_type`, or
-// one or more (repeated) `results`.
-message StreamingRecognizeResponse {
- // Indicates the type of speech event.
- enum SpeechEventType {
- // No speech event specified.
- SPEECH_EVENT_UNSPECIFIED = 0;
-
- // This event indicates that the server has detected the end of the user's
- // speech utterance and expects no additional speech. Therefore, the server
- // will not process additional audio (although it may subsequently return
- // additional results). The client should stop sending additional audio
- // data, half-close the gRPC connection, and wait for any additional results
- // until the server closes the gRPC connection. This event is only sent if
- // `single_utterance` was set to `true`, and is not used otherwise.
- END_OF_SINGLE_UTTERANCE = 1;
- }
-
- // [*Output only*] If set, returns a [google.rpc.Status][google.rpc.Status] message that
- // specifies the error for the operation.
- google.rpc.Status error = 1;
-
- // [*Output only*] This repeated list contains zero or more results that
- // correspond to consecutive portions of the audio currently being processed.
- // It contains zero or one `is_final=true` result (the newly settled portion),
- // followed by zero or more `is_final=false` results (the interim results).
- repeated StreamingRecognitionResult results = 2;
-
- // [*Output only*] Indicates the type of speech event.
- SpeechEventType speech_event_type = 4;
-}
-
-// A streaming speech recognition result corresponding to a portion of the audio
-// that is currently being processed.
-message StreamingRecognitionResult {
- // [**Extension by Techmo**]
- // Indicates the cause of recognition result finalization. These are MRCPv2-related.
- // See [Completion-Cause](https://tools.ietf.org/html/rfc6787#section-9.4.11).
- enum ResultFinalizationCause {
- // No recognition result finalization cause specified.
- RESULT_FINALIZATION_CAUSE_UNSPECIFIED = 0;
-
- // Recognition has been finalized with a complete result
- // after specified length of silence after user speech.
- // See [Speech-Complete-Timeout](https://tools.ietf.org/html/rfc6787#section-9.4.15).
- SUCCESS = 1;
-
- // Recognition has started and there was no speech detected
- // for a certain period of time.
- // See [No-Input-Timeout](https://tools.ietf.org/html/rfc6787#section-9.4.6).
- NO_INPUT_TIMEOUT = 2;
-
- // Recognition has been finalized because speech was too long, with a complete result.
- // See [Recognition-Timeout](https://tools.ietf.org/html/rfc6787#section-9.4.7).
- SUCCESS_MAXTIME = 3;
-
- // Recognition has been finalized with an incomplete result
- // after specified length of silence after user speech.
- // See [Speech-Incomplete-Timeout](https://tools.ietf.org/html/rfc6787#section-9.4.16).
- PARTIAL_MATCH = 4;
-
- // Recognition has been finalized because speech was too long, with no result.
- // See [Recognition-Timeout](https://tools.ietf.org/html/rfc6787#section-9.4.7).
- NO_MATCH_MAXTIME = 5;
- }
-
- // [*Output only*] May contain one or more recognition hypotheses (up to the
- // maximum specified in `max_alternatives`).
- // These alternatives are ordered in terms of accuracy, with the top (first)
- // alternative being the most probable, as ranked by the recognizer.
- repeated SpeechRecognitionAlternative alternatives = 1;
-
- // [*Output only*] If `false`, this `StreamingRecognitionResult` represents an
- // interim result that may change. If `true`, this is the final time the
- // speech service will return this particular `StreamingRecognitionResult`,
- // the recognizer will not return any further hypotheses for this portion of
- // the transcript and corresponding audio.
- bool is_final = 2;
-
- // @exclude [*Output only*] An estimate of the likelihood that the recognizer will not
- // change its guess about this interim result. Values range from 0.0
- // (completely unstable) to 1.0 (completely stable).
- // This field is only provided for interim results (`is_final=false`).
- // The default of 0.0 is a sentinel value indicating `stability` was not set.
-
- // [*Unused*]
- float stability = 3;
-
- // [**Extension by Techmo**]
- // [*Output only*] Indicates the cause of recognition result finalization.
- ResultFinalizationCause result_finalization_cause = 4;
-
- // [**Extension by Techmo**]
- // [*Output only*] Detailed recognition result (lattice).
- // Returned only when requested (`ConfigField`: return-lattice=true in
- // `RecognitionConfig` Message), only for final (`is_final = true`) results,
- // and only when it's allowed by licence.
- // When requested and not allowed by licence, [google.rpc.Code.FAILED_PRECONDITION]
- // will be returned.
- repeated RecognitionLattice lattice = 5;
-
- // [**Extension by Techmo**]
- // [*Output only*] Predicted gender of the speaker
- Gender gender = 6;
-
- // [**Extension by Techmo**]
- // [*Output only*] Predicted age of the speaker
- Age age = 7;
-}
-
-// A speech recognition result corresponding to a portion of the audio.
-message SpeechRecognitionResult {
- // [*Output only*] May contain one or more recognition hypotheses (up to the
- // maximum specified in `max_alternatives`).
- // These alternatives are ordered in terms of accuracy, with the top (first)
- // alternative being the most probable, as ranked by the recognizer.
- repeated SpeechRecognitionAlternative alternatives = 1;
-
- // [**Extension by Techmo**]
- // [*Output only*] Detailed recognition result (lattice).
- // Returned only when requested (`ConfigField`: return-lattice=true in
- // `RecognitionConfig` Message), only for final (`is_final = true`) results,
- // and only when it's allowed by licence.
- // When requested and not allowed by licence, [google.rpc.Code.FAILED_PRECONDITION]
- // will be returned.
- repeated RecognitionLattice lattice = 5;
-
- // [**Extension by Techmo**]
- // [*Output only*] Predicted gender of the speaker
- Gender gender = 6;
-
- // [**Extension by Techmo**]
- // [*Output only*] Predicted age of the speaker
- Age age = 7;
-}
-
-// Alternative hypotheses (a.k.a. n-best list).
-message SpeechRecognitionAlternative {
- // [*Output only*] Transcript text representing the words that the user spoke.
- string transcript = 1;
-
- // [*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.
- float confidence = 2;
-
- // @exclude 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.
-
- // [*Output only*] A list of word-specific information for each recognized word.
- repeated WordInfo words = 3;
-}
-
-// Word-specific information for recognized words. Word information is only
-// included in the response when certain request parameters are set, such
-// as `enable_word_time_offsets`.
-message WordInfo {
- // @exclude [*Output only*] Time offset relative to the beginning of the audio,
- // and corresponding to the start of the spoken word.
- // This field is only set if `enable_word_time_offsets=true` and only
- // in the top hypothesis.
- // This is an experimental feature and the accuracy of the time offset can
- // vary.
-
- // [*Output only*] Time offset relative to the beginning of the audio,
- // and corresponding to the start of the spoken word.
- // This field is only set if `enable_word_time_offsets=true`.
- google.protobuf.Duration start_time = 1;
-
- // @exclude [*Output only*] Time offset relative to the beginning of the audio,
- // and corresponding to the end of the spoken word.
- // This field is only set if `enable_word_time_offsets=true` and only
- // in the top hypothesis.
- // This is an experimental feature and the accuracy of the time offset can
- // vary.
-
- // [*Output only*] Time offset relative to the beginning of the audio,
- // and corresponding to the end of the spoken word.
- // This field is only set if `enable_word_time_offsets=true`.
- google.protobuf.Duration end_time = 2;
-
- // [*Output only*] The word corresponding to this set of information.
- string word = 3;
-}
-
-// [**Extension by Techmo**]
-// Detailed recognition result (lattice).
-// Returned only when requested (`ConfigField`: return-lattice=true in
-// `RecognitionConfig` Message), only for final (`is_final = true`) results,
-// and only when it's allowed by licence. When requested and not allowed by
-// licence, [google.rpc.Code.FAILED_PRECONDITION] will be returned.
-message RecognitionLattice {
- // List of final nodes.
- repeated int32 final_nodes = 1;
-
- // List of lattice edges.
- repeated LatticeEdge edges = 2;
-}
-
-// [**Extension by Techmo**]
-// Edge-specific information for recognition lattice.
-message LatticeEdge {
- // Input node ID, node '0' is starting node for the lattice.
- int32 start_node = 1;
-
- // End node ID.
- int32 end_node = 2;
-
- // Word.
- string symbol = 3;
-
- // Language model cost.
- float language_cost = 4;
-
- // Raw acoustic score (unscaled).
- float acoustic_cost = 5;
-
- // Word duration in milliseconds.
- int32 duration = 6;
-}
-
-// [**Extension by Techmo**]
-// Predicted gender of the speaker
-message Gender {
- // The recognized gender label.
- string gender = 1;
-
- // The confidence in [0, 1] range, where near 0 means 'unsure' and near 1 means 'almost certain'.
- float confidence = 2;
-}
-
-// [**Extension by Techmo**]
-// Predicted age of the speaker
-message Age {
- // The recognized age, in years.
- int32 age = 1;
-
- // The confidence in [0, 1] range, where near 0 means 'unsure' and near 1 means 'almost certain'.
- float confidence = 2;
-}
diff --git a/proto/techmo/asr/api/v1/asr.proto b/proto/techmo/asr/api/v1/asr.proto
deleted file mode 100644
index a83f414..0000000
--- a/proto/techmo/asr/api/v1/asr.proto
+++ /dev/null
@@ -1,436 +0,0 @@
-// Copyright 2023 Techmo sp. z o.o.
-
-syntax = "proto3";
-
-package techmo.asr.api.v1;
-
-import "google/protobuf/duration.proto";
-import "techmo/api/status.proto";
-
-
-// An automatic speech recognition (ASR) service providing a solution for
-// speech-to-text conversion extended by the assessment of additional speech
-// and speaker features.
-service Asr {
- // Perform bidirectional streaming recognition.
- rpc StreamingRecognize(stream StreamingRecognizeRequest)
- returns (stream StreamingRecognizeResponse) {}
-}
-
-// A message streamed from the client through
-// the [`StreamingRecognize`](#StreamingRecognize) method.
-message StreamingRecognizeRequest {
- oneof request_content {
- // The immutable initial configuration of the request.
- // Must be sent once in the request's first message.
- StreamingRecognizeRequestConfig config = 1;
-
- // The message controlling the processing flow of the request.
- // May be sent multiple times except in the request's first message.
- StreamingRecognizeRequestControlMessage control_message = 2;
-
- // The data contents of the request itself.
- // May be sent multiple times except in the request's first message.
- StreamingRecognizeRequestData data = 3;
- }
-}
-
-// A message holding configuration of
-// a [`StreamingRecognize`](#StreamingRecognize) request.
-message StreamingRecognizeRequestConfig {
- // Part of the configuration for the request's audio content.
- AudioConfig audio_config = 1;
-
- // Part of the configuration for the request's result form.
- ResultConfig result_config = 2;
-
- // Part of the configuration for the request's processing flow.
- StreamingConfig streaming_config = 3;
-
- // Part of the configuration for speech recognition.
- SpeechRecognitionConfig speech_recognition_config = 4;
-
- // Part of the configuration for age recognition.
- AgeRecognitionConfig age_recognition_config = 5;
-
- // Part of the configuration for gender recognition.
- GenderRecognitionConfig gender_recognition_config = 6;
-
- // Part of the configuration for language recognition.
- LanguageRecognitionConfig language_recognition_config = 7;
-}
-
-// Result configuration of
-// a [`StreamingRecognize`](#StreamingRecognize) request.
-message ResultConfig {
- // The switch that toggles continuous recognition into single utterance mode.
- // The service returns a final result for each end of utterance it detects in
- // the audio, which may occur multiple times during a request.
- // If enabled, the request terminates right after its first final result.
- bool enable_single_utterance = 1;
-
- // The switch that allows interim results.
- // If enabled, results containing tentative hypotheses may be returned in
- // addition to final ones.
- // The service should silently ignore this field if it is unsupported.
- bool enable_interim_results = 2;
-}
-
-// Streaming configuration of
-// a [`StreamingRecognize`](#StreamingRecognize) request.
-message StreamingConfig {
- reserved 1; // bool enable_single_utterance = 1;
-
- // The switch that enables manual control of the input timer.
- // The timer imposes two constraints: one that finalizes recognition after
- // a specified period unless speech is detected, and the other that limits
- // the total time for an utterance. Manual control allows recognition to
- // begin but delays enforcement of these constraints. The timer restarts
- // after each detected end of utterance (each final result).
- // If enabled, the timer does not start automatically. Instead, it can be
- // initiated by sending
- // a [`StreamingRecognizeRequestControlMessage`](#StreamingRecognizeRequestControlMessage)
- // with the `start_input_timer` field set to `true` as needed. This should
- // occur after the beginning of the request and be repeated after each final
- // result.
- bool enable_manual_input_timer = 2;
-}
-
-// Audio configuration of
-// a [`StreamingRecognize`](#StreamingRecognize) request.
-message AudioConfig {
- // The possible audio encodings.
- enum AudioEncoding {
- // Unspecified audio encoding.
- UNSPECIFIED = 0;
-
- // Linear pulse-code modulation of uncompressed 16-bit signed little-endian
- // samples.
- LINEAR16 = 1;
-
- // Free Lossless Audio Codec ([FLAC](https://wiki.xiph.org/FLAC)).
- // The encoding requires only about half the bandwidth of `LINEAR16`.
- // 16-bit and 24-bit samples. Not all fields in `STREAMINFO` are supported.
- // When set, the service ignores the `sampling_rate_hz` field and detects
- // the actual value from audio header instead.
- FLAC = 2;
-
- // Ogg Encapsulated Opus Audio Codec ([OggOpus](https://wiki.xiph.org/OggOpus)).
- // When set, the service ignores the `sampling_rate_hz` field and detects
- // the actual value from audio header instead.
- OGG_OPUS = 6;
-
- // MP3 (ISO/IEC 11172-3 and ISO/IEC 13818-3).
- // Only constant bitrate.
- // When set, the service ignores the `sampling_rate_hz` field and detects
- // the actual value from audio header instead.
- MP3 = 8;
- }
-
- // The encoding of the audio data sent in the request. Single channel (mono)
- // audio is assumed.
- // The service should respond with the `INVALID_ARGUMENT` gRPC status code
- // if the encoding is `UNSPECIFIED`.
- // The service should respond with the `FAILED_PRECONDITION` gRPC status code
- // if the encoding is not supported.
- AudioEncoding encoding = 1;
-
- // The sampling rate of the audio data sent in the request.
- // The service should silently ignore the field for encodings that are sent
- // along wtih headers, and detect the value from them instead.
- // The service should respond with the `INVALID_ARGUMENT` gRPC status code
- // if the value is not greater than 0.
- float sampling_rate_hz = 2;
-}
-
-// Configuration of age recognition.
-message AgeRecognitionConfig {
- // The switch that enables age recognition for the request.
- // If disabled or unspecified, the related results are excluded.
- // The service responds with the `FAILED_PRECONDITION` gRPC status code
- // if requested but not enabled.
- bool enable_age_recognition = 1;
-}
-
-// Configuration of gender recognition.
-message GenderRecognitionConfig {
- // The switch that enables gender recognition for the request.
- // If disabled or unspecified, the related results are excluded.
- // The service responds with the `FAILED_PRECONDITION` gRPC status code
- // if requested but not enabled.
- bool enable_gender_recognition = 1;
-}
-
-// Configuration of language recognition.
-message LanguageRecognitionConfig {
- // The switch that enables language recognition for the request.
- // If disabled or unspecified, the related results are excluded.
- // The service responds with the `FAILED_PRECONDITION` gRPC status code
- // if requested but not enabled.
- bool enable_language_recognition = 1;
-}
-
-// Configuration for speech recognition.
-message SpeechRecognitionConfig {
- // The switch that enables speech recognition for the request.
- // If disabled or unspecified, the related results are excluded.
- // The service responds with the `FAILED_PRECONDITION` gRPC status code
- // if requested but not enabled.
- bool enable_speech_recognition = 1;
-
- // The maximum number of alternative transcriptions allowed to be included
- // per response.
- // The actual count received can be less than the specified value and may
- // also be equal to 0. If unspecified or 0, one alternative is allowed to be
- // returned too.
- uint32 recognition_alternatives_limit = 2;
-
- // The switch that enables additional time alignment of recognitions in word
- // details.
- // If enabled, the `words` field of
- // a [`SpeechRecognitionAlternative`](#SpeechRecognitionAlternative) message
- // includes a list of [`SpeechRecognitionWord`](#SpeechRecognitionWord)
- // messages. Otherwise, it remains empty.
- // The service responds with the `FAILED_PRECONDITION` gRPC status code
- // if requested but not enabled.
- bool enable_time_alignment = 3;
-
- // The name of a language group of models to be used.
- // If left unspecified, it backs to the service's default group.
- // The service responds with the `NOT_FOUND` gRPC status code
- // if the name is not registered.
- string language_group_name = 4;
-
- // The name of a model to be used.
- // If left unspecified, it backs to the selected langugage group's default.
- // The service responds with the `NOT_FOUND` gRPC status code
- // if the name is not registered.
- string model_name = 5;
-
- // Deprecated.
- // The additional advanced service-dependend configuration for its speech
- // recognizer. It may be silently ignored.
- map