transcribev5

type AudioEncoding int32

type AudioFormatHeadered int32

type AudioFormatRAW struct {

	// Encoding of the samples. It must be specified explicitly and using the
	// default value of `AUDIO_ENCODING_UNSPECIFIED` will result in an error.
	Encoding AudioEncoding `protobuf:"varint,1,opt,name=encoding,proto3,enum=cobaltspeech.transcribe.v5.AudioEncoding" json:"encoding,omitempty"`
	// Bit depth of each sample (e.g. 8, 16, 24, 32, etc.). This is a required
	// field.
	BitDepth uint32 `protobuf:"varint,2,opt,name=bit_depth,json=bitDepth,proto3" json:"bit_depth,omitempty"`
	// Byte order of the samples. This field must be set to a value other than
	// `BYTE_ORDER_UNSPECIFIED` when the `bit_depth` is greater than 8.
	ByteOrder ByteOrder `` /* 131-byte string literal not displayed */
	// Sampling rate in Hz. This is a required field.
	SampleRate uint32 `protobuf:"varint,4,opt,name=sample_rate,json=sampleRate,proto3" json:"sample_rate,omitempty"`
	// Number of channels present in the audio. E.g.: 1 (mono), 2 (stereo), etc.
	// This is a required field.
	Channels uint32 `protobuf:"varint,5,opt,name=channels,proto3" json:"channels,omitempty"`
	// contains filtered or unexported fields
}

type ByteOrder int32

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"`
	// Features related to this arc
	Features *ConfusionNetworkArcFeatures `protobuf:"bytes,3,opt,name=features,proto3" json:"features,omitempty"`
	// contains filtered or unexported fields
}

type ConfusionNetworkArcFeatures struct {

	// A map of features that are used for recalculating confidence scores of this
	// confusion network arc
	Confidence map[string]float64 `` /* 163-byte string literal not displayed */
	// contains filtered or unexported fields
}

type ConfusionNetworkLink struct {

	// Time offset in milliseconds relative to the beginning of audio received by
	// the recognizer and corresponding to the start of this link
	StartTimeMs uint64 `protobuf:"varint,1,opt,name=start_time_ms,json=startTimeMs,proto3" json:"start_time_ms,omitempty"`
	// Duration in milliseconds of the current link in the confusion network
	DurationMs uint64 `protobuf:"varint,2,opt,name=duration_ms,json=durationMs,proto3" json:"duration_ms,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 factor is a positive number which is
	// used to multiply 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 factor.
	//
	// By default, all phrases or words provided in the `RecongitionContext` are
	// given an equal probability of occurring. Boost factors larger than 1 make
	// the phrase or word more probable and boost factors less than 1 make it less
	// likely. A boost factor of 2 corresponds to making the phrase or word twice
	// as likely, while a boost factor of 0.5 means half as likely.
	Boost float32 `protobuf:"fixed32,2,opt,name=boost,proto3" json:"boost,omitempty"`
	// contains filtered or unexported fields
}

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 may be
	// 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(native) 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"`
	// Audio sample rates other than the model's native sample rate(sample_rate) that can be accommodated
	SupportedSampleRates []uint32 `` /* 131-byte string literal not displayed */
	// 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
	// `transcript_raw`. 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".
	TranscriptFormatted string `protobuf:"bytes,1,opt,name=transcript_formatted,json=transcriptFormatted,proto3" json:"transcript_formatted,omitempty"`
	// Text representing the transcription of the words that the user spoke,
	// without any formatting applied. If you want the formatted transcript,
	// please see the field `transcript_formatted`.
	//
	// As an example, if the spoken utterance was `four people`, this field would
	// be set to "FOUR PEOPLE".
	TranscriptRaw string `protobuf:"bytes,2,opt,name=transcript_raw,json=transcriptRaw,proto3" json:"transcript_raw,omitempty"`
	// Time offset in milliseconds relative to the beginning of audio received by
	// the recognizer and corresponding to the start of this utterance.
	StartTimeMs uint64 `protobuf:"varint,3,opt,name=start_time_ms,json=startTimeMs,proto3" json:"start_time_ms,omitempty"`
	// Duration in milliseconds of the current utterance in the spoken audio.
	DurationMs uint64 `protobuf:"varint,4,opt,name=duration_ms,json=durationMs,proto3" json:"duration_ms,omitempty"`
	// Confidence estimate between 0 and 1. A higher number represents a higher
	// likelihood of the output being correct.
	Confidence float64 `protobuf:"fixed64,5,opt,name=confidence,proto3" json:"confidence,omitempty"`
	// Word-level details corresponding to the transcripts. This is available only
	// if `enable_word_details` was set to `true` in the `RecognitionConfig`.
	WordDetails *WordDetails `protobuf:"bytes,6,opt,name=word_details,json=wordDetails,proto3" json:"word_details,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"`
	// Format of the audio to be sent for recognition.
	//
	// Depending on how they are configured, server instances of this service may
	// not support all the formats provided in the API. One format that is
	// guaranteed to be supported is the RAW format with little-endian 16-bit
	// signed samples with the sample rate matching that of the model being
	// requested.
	//
	// Types that are assignable to AudioFormat:
	//
	//	*RecognitionConfig_AudioFormatRaw
	//	*RecognitionConfig_AudioFormatHeadered
	AudioFormat isRecognitionConfig_AudioFormat `protobuf_oneof:"audio_format"`
	// This is an optional field. If the audio has multiple channels, this field
	// can be configured with the list of channel indices that should be
	// considered for the recognition task. These channels are 0-indexed.
	//
	// Example: `[0]` for a mono file, `[0, 1]` for a stereo file.
	// Example: `[1]` to only transcribe the second channel of a stereo file.
	//
	// If this field is not set, all the channels in the audio will be processed.
	//
	// 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.
	SelectedAudioChannels []uint32 `` /* 134-byte string literal not displayed */
	// This is an optional field. It can be used to indicate that the audio being
	// streamed to the recognizer is offset from the original stream by the
	// provided duration in milliseconds. This offset will be added to all
	// timestamps in results returned by the recognizer.
	//
	// The default value of this field is 0ms, so the timestamps in the
	// recognition result will not be modified.
	//
	// Example use case where this field can be helpful: if a recognition session
	// was interrupted and audio needs to be sent to a new session from the point
	// where the session was previously interrupted, the offset could be set to
	// the point where the interruption had happened.
	AudioTimeOffsetMs uint64 `protobuf:"varint,5,opt,name=audio_time_offset_ms,json=audioTimeOffsetMs,proto3" json:"audio_time_offset_ms,omitempty"`
	// This is an optional field. If this is set to `true`, each result will
	// include word level details of the transcript. These details are specified
	// in the `WordDetails` message. If set to `false`, no word-level details will
	// be returned. The default is `false`.
	EnableWordDetails bool `protobuf:"varint,6,opt,name=enable_word_details,json=enableWordDetails,proto3" json:"enable_word_details,omitempty"`
	// This is an optional field. If this is set to true, each result 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
	// returning a confusion network, this field will have no effect. Tokens in
	// the confusion network always correspond to tokens in the `transcript_raw`
	// returned.
	EnableConfusionNetwork bool `` /* 130-byte string literal not displayed */
	// This is an optional field. If there is any metadata associated with the
	// audio being sent, use this field to provide it to the recognizer. 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,8,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,9,opt,name=context,proto3" json:"context,omitempty"`
	// contains filtered or unexported fields
}

type RecognitionConfig_AudioFormatHeadered struct {
	// Audio has a self-describing header. Headers are expected to be sent at
	// the beginning of the entire audio file/stream, and not in every
	// `RecognitionAudio` message.
	//
	// The default value of this type is AUDIO_FORMAT_HEADERED_UNSPECIFIED. If
	// this value is used, the server may attempt to detect the format of the
	// audio. However, it is recommended that the exact format be specified.
	AudioFormatHeadered AudioFormatHeadered `` /* 140-byte string literal not displayed */
}

type RecognitionConfig_AudioFormatRaw struct {
	// Audio is raw data without any headers
	AudioFormatRaw *AudioFormatRAW `protobuf:"bytes,2,opt,name=audio_format_raw,json=audioFormatRaw,proto3,oneof"`
}

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 RecognitionError struct {
	Message string `protobuf:"bytes,1,opt,name=message,proto3" json:"message,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 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. Channels
	// are 0-indexed, so the for mono audio data, this value will always be 0.
	AudioChannel uint32 `protobuf:"varint,4,opt,name=audio_channel,json=audioChannel,proto3" json:"audio_channel,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 StreamingRecognizeResponse struct {

	// A new recognition result. This field will be unset if a new result is not
	// yet available.
	Result *RecognitionResult `protobuf:"bytes,1,opt,name=result,proto3" json:"result,omitempty"`
	// A non-fatal error message. If a server encountered a non-fatal error when
	// processing the recognition request, it will be returned in this message.
	// The server will continue to process audio and produce further results.
	// Clients can continue streaming audio even after receiving these messages.
	// This error message is meant to be informational.
	//
	// An example of when these errors maybe produced: audio is sampled at a lower
	// rate than expected by model, producing possibly less accurate results.
	//
	// This field will be unset if there is no error to report.
	Error *RecognitionError `protobuf:"bytes,2,opt,name=error,proto3" json:"error,omitempty"`
	// contains filtered or unexported fields
}

type TranscribeServiceClient interface {
	// Queries the version of the server.
	Version(ctx context.Context, in *VersionRequest, 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 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) (TranscribeService_StreamingRecognizeClient, error)
	// Compiles recognition context information, such as a specialized list of
	// words or phrases, into a compact, efficient form to send with subsequent
	// `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 TranscribeServiceServer interface {
	// Queries the version of the server.
	Version(context.Context, *VersionRequest) (*VersionResponse, error)
	// Retrieves a list of available speech recognition models.
	ListModels(context.Context, *ListModelsRequest) (*ListModelsResponse, 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(TranscribeService_StreamingRecognizeServer) error
	// Compiles recognition context information, such as a specialized list of
	// words or phrases, into a compact, efficient form to send with subsequent
	// `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)
	// contains filtered or unexported methods
}

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

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

type UnimplementedTranscribeServiceServer struct {
}

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

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

type VersionResponse struct {

	// Version of the server handling these requests.
	Version string `protobuf:"bytes,1,opt,name=version,proto3" json:"version,omitempty"`
	// contains filtered or unexported fields
}

type WordDetails struct {

	// Word-level information corresponding to the `transcript_formatted` field.
	Formatted []*WordInfo `protobuf:"bytes,1,rep,name=formatted,proto3" json:"formatted,omitempty"`
	// Word-level information corresponding to the `transcript_raw` field.
	Raw []*WordInfo `protobuf:"bytes,2,rep,name=raw,proto3" json:"raw,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 in milliseconds relative to the beginning of audio received by
	// the recognizer and corresponding to the start of this spoken word.
	StartTimeMs uint64 `protobuf:"varint,3,opt,name=start_time_ms,json=startTimeMs,proto3" json:"start_time_ms,omitempty"`
	// Duration in milliseconds of the current word in the spoken audio.
	DurationMs uint64 `protobuf:"varint,4,opt,name=duration_ms,json=durationMs,proto3" json:"duration_ms,omitempty"`
	// contains filtered or unexported fields
}