asr

type AsrClient interface {
	// Performs synchronous speech recognition: receive results after all audio
	// has been sent and processed.
	Recognize(ctx context.Context, in *RecognizeRequest, opts ...grpc.CallOption) (*RecognizeResponse, error)
	// Performs asynchronous speech recognition: receive results via sogou.speech.longrunning.GetOperation interface
	LongRunningRecognize(ctx context.Context, in *LongRunningRecognizeRequest, opts ...grpc.CallOption) (*longrunning.Operation, error)
	// Performs bidirectional streaming speech recognition: receive results while
	// sending audio. This method is only available via the gRPC API (not REST).
	StreamingRecognize(ctx context.Context, opts ...grpc.CallOption) (Asr_StreamingRecognizeClient, error)
}

type AsrServer interface {
	// Performs synchronous speech recognition: receive results after all audio
	// has been sent and processed.
	Recognize(context.Context, *RecognizeRequest) (*RecognizeResponse, error)
	// Performs asynchronous speech recognition: receive results via sogou.speech.longrunning.GetOperation interface
	LongRunningRecognize(context.Context, *LongRunningRecognizeRequest) (*longrunning.Operation, error)
	// Performs bidirectional streaming speech recognition: receive results while
	// sending audio. This method is only available via the gRPC API (not REST).
	StreamingRecognize(Asr_StreamingRecognizeServer) error
	// contains filtered or unexported methods
}

type Asr_StreamingRecognizeClient interface {
	Send(*StreamingRecognizeRequest) error
	Recv() (*StreamingRecognizeResponse, error)
	grpc.ClientStream
}

type Asr_StreamingRecognizeServer interface {
	Send(*StreamingRecognizeResponse) error
	Recv() (*StreamingRecognizeRequest, error)
	grpc.ServerStream
}

type LongRunningRecognizeMetadata struct {

	// Approximate percentage of audio processed thus far. Guaranteed to be 100
	// when the audio is fully processed and the results are available.
	ProgressPercent int32 `protobuf:"varint,1,opt,name=progress_percent,json=progressPercent,proto3" json:"progress_percent,omitempty"`
	// Time when the request was received.
	StartTime *timestamppb.Timestamp `protobuf:"bytes,2,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
	// Time of the most recent processing update.
	LastUpdateTime *timestamppb.Timestamp `protobuf:"bytes,3,opt,name=last_update_time,json=lastUpdateTime,proto3" json:"last_update_time,omitempty"`
	// contains filtered or unexported fields
}

type LongRunningRecognizeRequest struct {

	// *Required* Provides information to the recognizer that specifies how to
	// process the request.
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
	// *Required* The audio data to be recognized.
	Audio *RecognitionAudio `protobuf:"bytes,2,opt,name=audio,proto3" json:"audio,omitempty"`
	// contains filtered or unexported fields
}

type LongRunningRecognizeResponse struct {
	Results []*SpeechRecognitionResult `protobuf:"bytes,1,rep,name=results,proto3" json:"results,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionAudio struct {

	// The audio source, which is either inline content or a uri.
	//
	// Types that are assignable to AudioSource:
	//	*RecognitionAudio_Content
	//	*RecognitionAudio_Uri
	AudioSource isRecognitionAudio_AudioSource `protobuf_oneof:"audio_source"`
	// contains filtered or unexported fields
}

type RecognitionAudio_Content struct {
	// 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.
	Content []byte `protobuf:"bytes,1,opt,name=content,proto3,oneof"`
}

type RecognitionAudio_Uri struct {
	// ** CURRENTLY SOGOU INTERNAL USE ONLY. **
	// URI that points to a file that contains audio data bytes as specified in
	// `RecognitionConfig`. Currently, only SOGOU INTERNAL URIs are
	// supported, (other URI formats return [google.rpc.Code.INVALID_ARGUMENT]).
	Uri string `protobuf:"bytes,2,opt,name=uri,proto3,oneof"`
}

type RecognitionConfig struct {

	// *Required* Encoding of audio data sent in all `RecognitionAudio` messages.
	Encoding RecognitionConfig_AudioEncoding `` /* 127-byte string literal not displayed */
	// *Required* Sample rate in Hertz of the audio data sent in all
	// `RecognitionAudio` messages.
	// In most cases, it should be specified as 16000.
	SampleRateHertz int32 `protobuf:"varint,2,opt,name=sample_rate_hertz,json=sampleRateHertz,proto3" json:"sample_rate_hertz,omitempty"`
	// *Required* The language code of the supplied audio.
	// Example: "zh-cmn-Hans-CN".
	// See [Language Support](https://zhiyin.sogou.com/doc/?url=/docs/content/asr/concepts/lauguages/) for a list of the currently supported language codes.
	LanguageCode string `protobuf:"bytes,3,opt,name=language_code,json=languageCode,proto3" json:"language_code,omitempty"`
	// *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`-`5`. A value of `0` or `1` will return 1.
	// If omitted, will return 1.
	MaxAlternatives int32 `protobuf:"varint,4,opt,name=max_alternatives,json=maxAlternatives,proto3" json:"max_alternatives,omitempty"`
	// *Optional* If set to `true`, the server will attempt to filter out
	// profanities
	ProfanityFilter bool `protobuf:"varint,5,opt,name=profanity_filter,json=profanityFilter,proto3" json:"profanity_filter,omitempty"`
	// *Optional* A means to provide context to assist the speech recognition.
	SpeechContexts []*SpeechContext `protobuf:"bytes,6,rep,name=speech_contexts,json=speechContexts,proto3" json:"speech_contexts,omitempty"`
	// *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`.
	EnableWordTimeOffsets bool `` /* 129-byte string literal not displayed */
	// *Optional* Metadata regarding this request.
	Metadata *RecognitionMetadata `protobuf:"bytes,9,opt,name=metadata,proto3" json:"metadata,omitempty"`
	// *Optional* If 'true', stop adds punctuation to recognition result hypotheses.
	// The default 'false' value DOES add punctuation to result hypotheses.
	DisableAutomaticPunctuation bool `` /* 146-byte string literal not displayed */
	// *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, "default" model is used.
	Model string `protobuf:"bytes,13,opt,name=model,proto3" json:"model,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionConfig_AudioEncoding int32

type RecognitionMetadata struct {

	// The audio type that most closely describes the audio being recognized.
	MicrophoneDistance RecognitionMetadata_MicrophoneDistance `` /* 180-byte string literal not displayed */
	// The name of device used to make the recording.
	RecordingDeviceName string `protobuf:"bytes,7,opt,name=recording_device_name,json=recordingDeviceName,proto3" json:"recording_device_name,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionMetadata_MicrophoneDistance int32

type RecognizeRequest struct {

	// *Required* Provides information to the recognizer that specifies how to
	// process the request.
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
	// *Required* The audio data to be recognized.
	Audio *RecognitionAudio `protobuf:"bytes,2,opt,name=audio,proto3" json:"audio,omitempty"`
	// contains filtered or unexported fields
}

type RecognizeResponse struct {

	// Output only. Sequential list of transcription results corresponding to
	// sequential portions of audio.
	Results []*SpeechRecognitionResult `protobuf:"bytes,1,rep,name=results,proto3" json:"results,omitempty"`
	// contains filtered or unexported fields
}

type SpeechContext struct {

	// *Optional* A list of strings containing words and phrases "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]
	Phrases []string `protobuf:"bytes,1,rep,name=phrases,proto3" json:"phrases,omitempty"`
	// contains filtered or unexported fields
}

type SpeechRecognitionAlternative struct {

	// *Output-only* Transcript text representing the words that the user spoke.
	Transcript string `protobuf:"bytes,1,opt,name=transcript,proto3" json:"transcript,omitempty"`
	// *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 typically provided only for the top hypothesis, and
	// only for `is_final=true` results. Clients should not rely on the
	// `confidence` field as it is not guaranteed to be accurate or consistent.
	// The default of 0.0 is a sentinel value indicating `confidence` was not set.
	Confidence float32 `protobuf:"fixed32,2,opt,name=confidence,proto3" json:"confidence,omitempty"`
	// *Output-only* A list of word-specific information for each recognized word.
	Words []*WordInfo `protobuf:"bytes,3,rep,name=words,proto3" json:"words,omitempty"`
	// contains filtered or unexported fields
}

type SpeechRecognitionResult struct {

	// 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.
	Alternatives []*SpeechRecognitionAlternative `protobuf:"bytes,1,rep,name=alternatives,proto3" json:"alternatives,omitempty"`
	// contains filtered or unexported fields
}

type StreamingRecognitionConfig struct {

	// *Required* Provides information to the recognizer that specifies how to
	// process the request.
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
	// *Optional* If `false` or omitted, the recognizer will perform continuous
	// recognition (continuing to wait for and process audio even if the user
	// pauses speaking) until the client closes the input stream (gRPC API) or
	// until the maximum time limit has been reached. May return multiple
	// `StreamingRecognitionResult`s with the `is_final` flag set to `true`.
	//
	// If `true`, the recognizer will detect a single spoken utterance. When it
	// detects that the user has paused or stopped speaking, it will return an
	// `END_OF_SINGLE_UTTERANCE` event and cease recognition. It will return no
	// more than one `StreamingRecognitionResult` with the `is_final` flag set to
	// `true`.
	SingleUtterance bool `protobuf:"varint,2,opt,name=single_utterance,json=singleUtterance,proto3" json:"single_utterance,omitempty"`
	// *Optional* If `true`, interim results (tentative hypotheses) may be
	// returned as they become available (these interim results are indicated with
	// the `is_final=false` flag).
	// If `false` or omitted, only `is_final=true` result(s) are returned.
	InterimResults bool `protobuf:"varint,3,opt,name=interim_results,json=interimResults,proto3" json:"interim_results,omitempty"`
	// *Optional* If `true`, adds punctuation to interim recognition result hypotheses.
	// available only if RecognitionConfig.disable_automatic_punctuation = false AND interim_results = true
	//
	// NOTE: deprecated
	EnableInterimResultsPunctuation bool `` /* 159-byte string literal not displayed */
	// *Optional* similar to `single_utterance`. But if `true`,
	// the recognizer will NOT detect any single spoken utterance
	// until the client closes the input stream (gRPC API) or
	// until the maximum time limit has been reached (approximately 30 seconds).
	// It will return only one `StreamingRecognitionResult`s with the `is_final` set to `true`.
	MergeUtterance bool `protobuf:"varint,5,opt,name=merge_utterance,json=mergeUtterance,proto3" json:"merge_utterance,omitempty"`
	// contains filtered or unexported fields
}

type StreamingRecognitionResult struct {

	// *Output-only* May contain one or more recognition hypotheses (up to the
	// maximum specified in `max_alternatives`).
	Alternatives []*SpeechRecognitionAlternative `protobuf:"bytes,1,rep,name=alternatives,proto3" json:"alternatives,omitempty"`
	// *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.
	IsFinal bool `protobuf:"varint,2,opt,name=is_final,json=isFinal,proto3" json:"is_final,omitempty"`
	// *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.
	Stability float32 `protobuf:"fixed32,3,opt,name=stability,proto3" json:"stability,omitempty"`
	// contains filtered or unexported fields
}

type StreamingRecognizeRequest struct {

	// The streaming request, which is either a streaming config or audio content.
	//
	// Types that are assignable to StreamingRequest:
	//	*StreamingRecognizeRequest_StreamingConfig
	//	*StreamingRecognizeRequest_AudioContent
	StreamingRequest isStreamingRecognizeRequest_StreamingRequest `protobuf_oneof:"streaming_request"`
	// contains filtered or unexported fields
}

type StreamingRecognizeRequest_AudioContent struct {
	// The audio data to be recognized. Sequential chunks of audio data are sent
	// in sequential `StreamingRecognizeRequest` messages. The first
	// `StreamingRecognizeRequest` message must not contain `audio_content` data
	// and all subsequent `StreamingRecognizeRequest` messages must contain
	// `audio_content` data. The audio bytes must be encoded as specified in
	// `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
	// pure binary representation (not base64).
	AudioContent []byte `protobuf:"bytes,2,opt,name=audio_content,json=audioContent,proto3,oneof"`
}

type StreamingRecognizeRequest_StreamingConfig struct {
	// Provides information to the recognizer that specifies how to process the
	// request. The first `StreamingRecognizeRequest` message must contain a
	// `streaming_config`  message.
	StreamingConfig *StreamingRecognitionConfig `protobuf:"bytes,1,opt,name=streaming_config,json=streamingConfig,proto3,oneof"`
}

type StreamingRecognizeResponse struct {

	// *Output-only* If set, returns a [google.rpc.Status] message that
	// specifies the error for the operation.
	Error *status.Status `protobuf:"bytes,1,opt,name=error,proto3" json:"error,omitempty"`
	// *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 more `is_final=false` results followed by zero or one
	// `is_final=true` result (the newly settled portion).
	Results []*StreamingRecognitionResult `protobuf:"bytes,2,rep,name=results,proto3" json:"results,omitempty"`
	// *Output-only* Indicates the type of speech event.
	SpeechEventType StreamingRecognizeResponse_SpeechEventType `` /* 177-byte string literal not displayed */
	// contains filtered or unexported fields
}

type StreamingRecognizeResponse_SpeechEventType int32

type UnimplementedAsrServer struct {
}

type UnsafeAsrServer interface {
	// contains filtered or unexported methods
}

type WordInfo struct {

	// *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.
	StartTime *durationpb.Duration `protobuf:"bytes,1,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
	// *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.
	EndTime *durationpb.Duration `protobuf:"bytes,2,opt,name=end_time,json=endTime,proto3" json:"end_time,omitempty"`
	// *Output-only* The word corresponding to this set of information.
	Word string `protobuf:"bytes,3,opt,name=word,proto3" json:"word,omitempty"`
	// contains filtered or unexported fields
}