cubicpb

type CompileContextRequest struct {

	// Unique identifier of the model to compile the context information for. The
	// model chosen needs to support context which can be verified by checking its
	// `ModelAttributes.ContextInfo` obtained via `ListModels`.
	ModelId string `protobuf:"bytes,1,opt,name=model_id,json=modelId,proto3" json:"model_id,omitempty"`
	// The token that is associated with the provided list of phrases or words
	// (e.g "menu_item", "airport" etc.). Must be one of the tokens included in
	// the model being used, which can be retrieved by calling the `ListModels`
	// method.
	Token string `protobuf:"bytes,2,opt,name=token,proto3" json:"token,omitempty"`
	// List of phrases and/or words to be compiled.
	Phrases []*ContextPhrase `protobuf:"bytes,3,rep,name=phrases,proto3" json:"phrases,omitempty"`
	// contains filtered or unexported fields
}

type CompileContextResponse struct {

	// Context information in a compact form that is efficient for use in
	// subsequent recognition requests. The size of the compiled form will depend
	// on the amount of text that was sent for compilation. For 1000 words it's
	// generally less than 100 kilobytes.
	Context *CompiledContext `protobuf:"bytes,1,opt,name=context,proto3" json:"context,omitempty"`
	// contains filtered or unexported fields
}

type CompiledContext struct {

	// The context information compiled by the `CompileContext` method.
	Data []byte `protobuf:"bytes,1,opt,name=data,proto3" json:"data,omitempty"`
	// contains filtered or unexported fields
}

type ConfusionNetworkArc struct {

	// Word in the recognized transcript
	Word string `protobuf:"bytes,1,opt,name=word,proto3" json:"word,omitempty"`
	// Confidence estimate between 0 and 1.  A higher number represents a higher
	// likelihood that the word was correctly recognized.
	Confidence float64 `protobuf:"fixed64,2,opt,name=confidence,proto3" json:"confidence,omitempty"`
	// contains filtered or unexported fields
}

type ConfusionNetworkLink struct {

	// Time offset relative to the beginning of audio received by the recognizer
	// and corresponding to the start of this link
	StartTime *duration.Duration `protobuf:"bytes,1,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
	// Duration of the current link in the confusion network
	Duration *duration.Duration `protobuf:"bytes,2,opt,name=duration,proto3" json:"duration,omitempty"`
	// Arcs between this link
	Arcs []*ConfusionNetworkArc `protobuf:"bytes,3,rep,name=arcs,proto3" json:"arcs,omitempty"`
	// contains filtered or unexported fields
}

type ContextInfo struct {

	// If this is set to true, the model supports taking context information into
	// account to aid speech recognition. The information may be sent with with
	// recognition requests via RecognitionContext inside RecognitionConfig.
	SupportsContext bool `protobuf:"varint,1,opt,name=supports_context,json=supportsContext,proto3" json:"supports_context,omitempty"`
	// A list of tokens (e.g "name", "airport" etc.) that serve has placeholders
	// in the model where a client provided list of phrases or words may be used
	// to aid speech recognition and produce the exact desired recognition output.
	AllowedContextTokens []string `protobuf:"bytes,2,rep,name=allowed_context_tokens,json=allowedContextTokens,proto3" json:"allowed_context_tokens,omitempty"`
	// contains filtered or unexported fields
}

type ContextPhrase struct {

	// The actual phrase or word.
	Text string `protobuf:"bytes,1,opt,name=text,proto3" json:"text,omitempty"`
	// This is an optional field. The boost value is a positive number which is
	// used to increase the probability of the phrase or word appearing in the
	// output. This setting can be used to differentiate between similar sounding
	// words, with the desired word given a bigger boost value.
	//
	// By default, all phrases or words are given an equal probability of 1/N
	// (where N = total number of phrases or words). If a boost value is provided,
	// the new probability is (boost + 1) * 1/N. We normalize the boosted
	// probabilities for all the phrases or words so that they sum to one. This
	// means that the boost value only has an effect if there are relative
	// differences in the values for different phrases or words. That is, if all
	// phrases or words have the same boost value, after normalization they will
	// all still have the same probability. This also means that the boost value
	// can be any positive value, but it is best to stick between 0 to 20.
	//
	// Negative values are not supported and will be treated as 0 values.
	Boost float32 `protobuf:"fixed32,2,opt,name=boost,proto3" json:"boost,omitempty"`
	// contains filtered or unexported fields
}

type CubicClient interface {
	// Queries the Version of the Server
	Version(ctx context.Context, in *empty.Empty, opts ...grpc.CallOption) (*VersionResponse, error)
	// Retrieves a list of available speech recognition models
	ListModels(ctx context.Context, in *ListModelsRequest, opts ...grpc.CallOption) (*ListModelsResponse, error)
	// Performs synchronous speech recognition: receive results after all audio
	// has been sent and processed.  It is expected that this request be typically
	// used for short audio content: less than a minute long.  For longer content,
	// the `StreamingRecognize` method should be preferred.
	Recognize(ctx context.Context, in *RecognizeRequest, opts ...grpc.CallOption) (*RecognitionResponse, error)
	// Performs bidirectional streaming speech recognition.  Receive results while
	// sending audio.  This method is only available via GRPC and not via
	// HTTP+JSON. However, a web browser may use websockets to use this service.
	StreamingRecognize(ctx context.Context, opts ...grpc.CallOption) (Cubic_StreamingRecognizeClient, error)
	// Compiles recognition context information, such as a specialized list of
	// words or phrases, into a compact, efficient form to send with subsequent
	// `Recognize` or `StreamingRecognize` requests to customize speech
	// recognition. For example, a list of contact names may be compiled in a
	// mobile app and sent with each recognition request so that the app user's
	// contact names are more likely to be recognized than arbitrary names. This
	// pre-compilation ensures that there is no added latency for the recognition
	// request. It is important to note that in order to compile context for a
	// model, that model has to support context in the first place, which can be
	// verified by checking its `ModelAttributes.ContextInfo` obtained via the
	// `ListModels` method. Also, the compiled data will be model specific; that
	// is, the data compiled for one model will generally not be usable with a
	// different model.
	CompileContext(ctx context.Context, in *CompileContextRequest, opts ...grpc.CallOption) (*CompileContextResponse, error)
}

type CubicServer interface {
	// Queries the Version of the Server
	Version(context.Context, *empty.Empty) (*VersionResponse, error)
	// Retrieves a list of available speech recognition models
	ListModels(context.Context, *ListModelsRequest) (*ListModelsResponse, error)
	// Performs synchronous speech recognition: receive results after all audio
	// has been sent and processed.  It is expected that this request be typically
	// used for short audio content: less than a minute long.  For longer content,
	// the `StreamingRecognize` method should be preferred.
	Recognize(context.Context, *RecognizeRequest) (*RecognitionResponse, error)
	// Performs bidirectional streaming speech recognition.  Receive results while
	// sending audio.  This method is only available via GRPC and not via
	// HTTP+JSON. However, a web browser may use websockets to use this service.
	StreamingRecognize(Cubic_StreamingRecognizeServer) error
	// Compiles recognition context information, such as a specialized list of
	// words or phrases, into a compact, efficient form to send with subsequent
	// `Recognize` or `StreamingRecognize` requests to customize speech
	// recognition. For example, a list of contact names may be compiled in a
	// mobile app and sent with each recognition request so that the app user's
	// contact names are more likely to be recognized than arbitrary names. This
	// pre-compilation ensures that there is no added latency for the recognition
	// request. It is important to note that in order to compile context for a
	// model, that model has to support context in the first place, which can be
	// verified by checking its `ModelAttributes.ContextInfo` obtained via the
	// `ListModels` method. Also, the compiled data will be model specific; that
	// is, the data compiled for one model will generally not be usable with a
	// different model.
	CompileContext(context.Context, *CompileContextRequest) (*CompileContextResponse, error)
}

type Cubic_StreamingRecognizeClient interface {
	Send(*StreamingRecognizeRequest) error
	Recv() (*RecognitionResponse, error)
	grpc.ClientStream
}

type Cubic_StreamingRecognizeServer interface {
	Send(*RecognitionResponse) error
	Recv() (*StreamingRecognizeRequest, error)
	grpc.ServerStream
}

type ListModelsRequest struct {
	// contains filtered or unexported fields
}

type ListModelsResponse struct {

	// List of models available for use that match the request.
	Models []*Model `protobuf:"bytes,1,rep,name=models,proto3" json:"models,omitempty"`
	// contains filtered or unexported fields
}

type Model struct {

	// Unique identifier of the model.  This identifier is used to choose the
	// model that should be used for recognition, and is specified in the
	// `RecognitionConfig` message.
	Id string `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	// Model name.  This is a concise name describing the model, and maybe
	// presented to the end-user, for example, to help choose which model to use
	// for their recognition task.
	Name string `protobuf:"bytes,2,opt,name=name,proto3" json:"name,omitempty"`
	// Model attributes
	Attributes *ModelAttributes `protobuf:"bytes,3,opt,name=attributes,proto3" json:"attributes,omitempty"`
	// contains filtered or unexported fields
}

type ModelAttributes struct {

	// Audio sample rate supported by the model
	SampleRate uint32 `protobuf:"varint,1,opt,name=sample_rate,json=sampleRate,proto3" json:"sample_rate,omitempty"`
	// Attributes specifc to supporting recognition context.
	ContextInfo *ContextInfo `protobuf:"bytes,2,opt,name=context_info,json=contextInfo,proto3" json:"context_info,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionAlternative struct {

	// Text representing the transcription of the words that the user spoke.
	//
	// The transcript will be formatted according to the servers formatting
	// configuration. If you want the raw transcript, please see the field
	// `raw_transcript`.  If the server is configured to not use any formatting,
	// then this field will contain the raw transcript.
	//
	// As an example, if the spoken utterance was "four people", and the
	// server was configured to format numbers, this field would be set to
	// "4 people".
	Transcript string `protobuf:"bytes,1,opt,name=transcript,proto3" json:"transcript,omitempty"`
	// Text representing the transcription of the words that the user spoke,
	// without any formatting.  This field will be populated only the config
	// `RecognitionConfig.enable_raw_transcript` is set to true. Otherwise this
	// field will be an empty string. If you want the formatted transcript, please
	// see the field `transcript`.
	//
	// As an example, if the spoken utterance was `here are four words`,
	// this field would be set to "HERE ARE FOUR WORDS".
	RawTranscript string `protobuf:"bytes,6,opt,name=raw_transcript,json=rawTranscript,proto3" json:"raw_transcript,omitempty"`
	// Confidence estimate between 0 and 1. A higher number represents a higher
	// likelihood of the output being correct.
	Confidence float64 `protobuf:"fixed64,2,opt,name=confidence,proto3" json:"confidence,omitempty"`
	// A list of word-specific information for each recognized word in the
	// `transcript` field. This is available only if `enable_word_confidence` or
	// `enable_word_time_offsets` was set to `true` in the `RecognitionConfig`.
	Words []*WordInfo `protobuf:"bytes,3,rep,name=words,proto3" json:"words,omitempty"`
	// A list of word-specific information for each recognized word in the
	// `raw_transcript` field. This is available only if `enable_word_confidence`
	// or `enable_word_time_offsets` was set to `true` _and_
	// `enable_raw_transcript` is also set to `true` in the `RecognitionConfig`.
	RawWords []*WordInfo `protobuf:"bytes,7,rep,name=raw_words,json=rawWords,proto3" json:"raw_words,omitempty"`
	// Time offset relative to the beginning of audio received by the recognizer
	// and corresponding to the start of this utterance.
	StartTime *duration.Duration `protobuf:"bytes,4,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
	// Duration of the current utterance in the spoken audio.
	Duration *duration.Duration `protobuf:"bytes,5,opt,name=duration,proto3" json:"duration,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionAudio struct {
	Data []byte `protobuf:"bytes,1,opt,name=data,proto3" json:"data,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionConfig struct {

	// Unique identifier of the model to use, as obtained from a `Model` message.
	ModelId string `protobuf:"bytes,1,opt,name=model_id,json=modelId,proto3" json:"model_id,omitempty"`
	// Encoding of audio data sent/streamed through the `RecognitionAudio`
	// messages.  For encodings like WAV/MP3 that have headers, the headers are
	// expected to be sent at the beginning of the stream, not in every
	// `RecognitionAudio` message.
	//
	// If not specified, the default encoding is RAW_LINEAR16.
	//
	// Depending on how they are configured, server instances of this service may
	// not support all the encodings enumerated above. They are always required to
	// accept RAW_LINEAR16.  If any other `Encoding` is specified, and it is not
	// available on the server being used, the recognition request will result in
	// an appropriate error message.
	AudioEncoding RecognitionConfig_Encoding `` /* 152-byte string literal not displayed */
	// Idle Timeout of the created Recognizer.  If no audio data is received by
	// the recognizer for this duration, ongoing rpc calls will result in an
	// error, the recognizer will be destroyed and thus more audio may not be sent
	// to the same recognizer.  The server may impose a limit on the maximum idle
	// timeout that can be specified, and if the value in this message exceeds
	// that serverside value, creating of the recognizer will fail with an error.
	IdleTimeout *duration.Duration `protobuf:"bytes,3,opt,name=idle_timeout,json=idleTimeout,proto3" json:"idle_timeout,omitempty"`
	// This is an optional field.  If this is set to true, each result will
	// include a list of words and the start time offset (timestamp) and the
	// duration for each of those words.  If set to `false`, no word-level
	// timestamps will be returned.  The default is `false`.
	EnableWordTimeOffsets bool `` /* 129-byte string literal not displayed */
	// This is an optional field.  If this is set to true, each result will
	// include a list of words and the confidence for those words.  If `false`, no
	// word-level confidence information is returned.  The default is `false`.
	EnableWordConfidence bool `protobuf:"varint,5,opt,name=enable_word_confidence,json=enableWordConfidence,proto3" json:"enable_word_confidence,omitempty"`
	// This is an optional field.  If this is set to true, the field
	// `RecognitionAlternative.raw_transcript` will be populated with the raw
	// transcripts output from the recognizer will be exposed without any
	// formatting rules applied.  If this is set to false, that field will not
	// be set in the results.  The RecognitionAlternative.transcript will
	// always be populated with text formatted according to the server's settings.
	EnableRawTranscript bool `protobuf:"varint,6,opt,name=enable_raw_transcript,json=enableRawTranscript,proto3" json:"enable_raw_transcript,omitempty"`
	// This is an optional field.  If this is set to true, the results will
	// include a confusion network.  If set to `false`, no confusion network will
	// be returned.  The default is `false`.  If the model being used does not
	// support a confusion network, results may be returned without a confusion
	// network available.  If this field is set to `true`, then
	// `enable_raw_transcript` is also forced to be true.
	EnableConfusionNetwork bool `` /* 130-byte string literal not displayed */
	// This is an optional field.  If the audio has multiple channels, this field
	// should be configured with the list of channel indices that should be
	// transcribed.  Channels are 0-indexed.
	//
	// Example: `[0]` for a mono file, `[0, 1]` for a stereo file.
	//
	// If this field is not set, a mono file will be assumed by default and only
	// channel-0 will be transcribed even if the file actually has additional
	// channels.
	//
	// Channels that are present in the audio may be omitted, but it is an error
	// to include a channel index in this field that is not present in the audio.
	// Channels may be listed in any order but the same index may not be repeated
	// in this list.
	//
	// BAD: `[0, 2]` for a stereo file; BAD: `[0, 0]` for a mono file.
	AudioChannels []uint32 `protobuf:"varint,8,rep,packed,name=audio_channels,json=audioChannels,proto3" json:"audio_channels,omitempty"`
	// This is an optional field.  If there is any metadata associated with the
	// audio being sent, use this field to provide it to cubic.  The server may
	// record this metadata when processing the request.  The server does not use
	// this field for any other purpose.
	Metadata *RecognitionMetadata `protobuf:"bytes,9,opt,name=metadata,proto3" json:"metadata,omitempty"`
	// This is an optional field for providing any additional context information
	// that may aid speech recognition.  This can also be used to add
	// out-of-vocabulary words to the model or boost recognition of specific
	// proper names or commands. Context information must be pre-compiled via the
	// `CompileContext()` method.
	Context *RecognitionContext `protobuf:"bytes,10,opt,name=context,proto3" json:"context,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionConfig_Encoding int32

type RecognitionConfusionNetwork struct {
	Links []*ConfusionNetworkLink `protobuf:"bytes,1,rep,name=links,proto3" json:"links,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionContext struct {

	// List of compiled context information, with each entry being compiled from a
	// list of words or phrases using the `CompileContext` method.
	Compiled []*CompiledContext `protobuf:"bytes,1,rep,name=compiled,proto3" json:"compiled,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionMetadata struct {

	// Any custom metadata that the client wants to associate with the recording.
	// This could be a simple string (e.g. a tracing ID) or structured data
	// (e.g. JSON)
	CustomMetadata string `protobuf:"bytes,1,opt,name=custom_metadata,json=customMetadata,proto3" json:"custom_metadata,omitempty"`
	// contains filtered or unexported fields
}

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

type RecognitionResult struct {

	// An n-best list of recognition hypotheses alternatives
	Alternatives []*RecognitionAlternative `protobuf:"bytes,1,rep,name=alternatives,proto3" json:"alternatives,omitempty"`
	// If this is set to true, it denotes that the result is an interim partial
	// result, and could change after more audio is processed.  If unset, or set
	// to false, it denotes that this is a final result and will not change.
	//
	// Servers are not required to implement support for returning partial
	// results, and clients should generally not depend on their availability.
	IsPartial bool `protobuf:"varint,2,opt,name=is_partial,json=isPartial,proto3" json:"is_partial,omitempty"`
	// If `enable_confusion_network` was set to true in the `RecognitionConfig`,
	// and if the model supports it, a confusion network will be available in the
	// results.
	Cnet *RecognitionConfusionNetwork `protobuf:"bytes,3,opt,name=cnet,proto3" json:"cnet,omitempty"`
	// Channel of the audio file that this result was transcribed from.  For a
	// mono file, or RAW_LINEAR16 input, this will be set to 0.
	AudioChannel uint32 `protobuf:"varint,4,opt,name=audio_channel,json=audioChannel,proto3" json:"audio_channel,omitempty"`
	// contains filtered or unexported fields
}

type RecognizeRequest struct {

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

type StreamingRecognizeRequest struct {

	// Types that are assignable to Request:
	//	*StreamingRecognizeRequest_Config
	//	*StreamingRecognizeRequest_Audio
	Request isStreamingRecognizeRequest_Request `protobuf_oneof:"request"`
	// contains filtered or unexported fields
}

type StreamingRecognizeRequest_Audio struct {
	Audio *RecognitionAudio `protobuf:"bytes,2,opt,name=audio,proto3,oneof"`
}

type StreamingRecognizeRequest_Config struct {
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3,oneof"`
}

type UnimplementedCubicServer struct {
}

type VersionResponse struct {

	// version of the cubic library handling the recognition
	Cubic string `protobuf:"bytes,1,opt,name=cubic,proto3" json:"cubic,omitempty"`
	// version of the server handling these requests
	Server string `protobuf:"bytes,2,opt,name=server,proto3" json:"server,omitempty"`
	// contains filtered or unexported fields
}

type WordInfo struct {

	// The actual word in the text
	Word string `protobuf:"bytes,1,opt,name=word,proto3" json:"word,omitempty"`
	// Confidence estimate between 0 and 1.  A higher number represents a
	// higher likelihood that the word was correctly recognized.
	Confidence float64 `protobuf:"fixed64,2,opt,name=confidence,proto3" json:"confidence,omitempty"`
	// Time offset relative to the beginning of audio received by the recognizer
	// and corresponding to the start of this spoken word.
	StartTime *duration.Duration `protobuf:"bytes,3,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
	// Duration of the current word in the spoken audio.
	Duration *duration.Duration `protobuf:"bytes,4,opt,name=duration,proto3" json:"duration,omitempty"`
	// contains filtered or unexported fields
}