speech

package
v0.0.0-...-52d6a69 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Jun 19, 2019 License: Apache-2.0, Apache-2.0 Imports: 11 Imported by: 0

Documentation

Overview

Package speech is a generated protocol buffer package.

It is generated from these files: 

google/cloud/speech/v1/cloud_speech.proto

It has these top-level messages: 

RecognizeRequest
LongRunningRecognizeRequest
StreamingRecognizeRequest
StreamingRecognitionConfig
RecognitionConfig
SpeechContext
RecognitionAudio
RecognizeResponse
LongRunningRecognizeResponse
LongRunningRecognizeMetadata
StreamingRecognizeResponse
StreamingRecognitionResult
SpeechRecognitionResult
SpeechRecognitionAlternative
WordInfo

Index

Constants

This section is empty.

Variables

View Source 
var RecognitionConfig_AudioEncoding_name = map[int32]string{
	0: "ENCODING_UNSPECIFIED",
	1: "LINEAR16",
	2: "FLAC",
	3: "MULAW",
	4: "AMR",
	5: "AMR_WB",
	6: "OGG_OPUS",
	7: "SPEEX_WITH_HEADER_BYTE",
}
View Source 
var RecognitionConfig_AudioEncoding_value = map[string]int32{
	"ENCODING_UNSPECIFIED":   0,
	"LINEAR16":               1,
	"FLAC":                   2,
	"MULAW":                  3,
	"AMR":                    4,
	"AMR_WB":                 5,
	"OGG_OPUS":               6,
	"SPEEX_WITH_HEADER_BYTE": 7,
}
View Source 
var StreamingRecognizeResponse_SpeechEventType_name = map[int32]string{
	0: "SPEECH_EVENT_UNSPECIFIED",
	1: "END_OF_SINGLE_UTTERANCE",
}
View Source 
var StreamingRecognizeResponse_SpeechEventType_value = map[string]int32{
	"SPEECH_EVENT_UNSPECIFIED": 0,
	"END_OF_SINGLE_UTTERANCE":  1,
}

Functions

func RegisterSpeechServer 

func RegisterSpeechServer(s *grpc.Server, srv SpeechServer)

Types

type LongRunningRecognizeMetadata 

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" json:"progress_percent,omitempty"`
	// Time when the request was received.
	StartTime *google_protobuf4.Timestamp `protobuf:"bytes,2,opt,name=start_time,json=startTime" json:"start_time,omitempty"`
	// Time of the most recent processing update.
	LastUpdateTime *google_protobuf4.Timestamp `protobuf:"bytes,3,opt,name=last_update_time,json=lastUpdateTime" json:"last_update_time,omitempty"`
}

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.

func (*LongRunningRecognizeMetadata) Descriptor 

func (*LongRunningRecognizeMetadata) Descriptor() ([]byte, []int)

func (*LongRunningRecognizeMetadata) GetLastUpdateTime 

func (m *LongRunningRecognizeMetadata) GetLastUpdateTime() *google_protobuf4.Timestamp

func (*LongRunningRecognizeMetadata) GetProgressPercent 

func (m *LongRunningRecognizeMetadata) GetProgressPercent() int32

func (*LongRunningRecognizeMetadata) GetStartTime 

func (m *LongRunningRecognizeMetadata) GetStartTime() *google_protobuf4.Timestamp

func (*LongRunningRecognizeMetadata) ProtoMessage 

func (*LongRunningRecognizeMetadata) ProtoMessage()

func (*LongRunningRecognizeMetadata) Reset 

func (m *LongRunningRecognizeMetadata) Reset()

func (*LongRunningRecognizeMetadata) String 

func (m *LongRunningRecognizeMetadata) String() string

type LongRunningRecognizeRequest 

type LongRunningRecognizeRequest struct {
	// *Required* Provides information to the recognizer that specifies how to
	// process the request.
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config" json:"config,omitempty"`
	// *Required* The audio data to be recognized.
	Audio *RecognitionAudio `protobuf:"bytes,2,opt,name=audio" json:"audio,omitempty"`
}

The top-level message sent by the client for the `LongRunningRecognize` method.

func (*LongRunningRecognizeRequest) Descriptor 

func (*LongRunningRecognizeRequest) Descriptor() ([]byte, []int)

func (*LongRunningRecognizeRequest) GetAudio 

func (m *LongRunningRecognizeRequest) GetAudio() *RecognitionAudio

func (*LongRunningRecognizeRequest) GetConfig 

func (m *LongRunningRecognizeRequest) GetConfig() *RecognitionConfig

func (*LongRunningRecognizeRequest) ProtoMessage 

func (*LongRunningRecognizeRequest) ProtoMessage()

func (*LongRunningRecognizeRequest) Reset 

func (m *LongRunningRecognizeRequest) Reset()

func (*LongRunningRecognizeRequest) String 

func (m *LongRunningRecognizeRequest) String() string

type LongRunningRecognizeResponse 

type LongRunningRecognizeResponse struct {
	// *Output-only* Sequential list of transcription results corresponding to
	// sequential portions of audio.
	Results []*SpeechRecognitionResult `protobuf:"bytes,2,rep,name=results" json:"results,omitempty"`
}

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.

func (*LongRunningRecognizeResponse) Descriptor 

func (*LongRunningRecognizeResponse) Descriptor() ([]byte, []int)

func (*LongRunningRecognizeResponse) GetResults 

func (m *LongRunningRecognizeResponse) GetResults() []*SpeechRecognitionResult

func (*LongRunningRecognizeResponse) ProtoMessage 

func (*LongRunningRecognizeResponse) ProtoMessage()

func (*LongRunningRecognizeResponse) Reset 

func (m *LongRunningRecognizeResponse) Reset()

func (*LongRunningRecognizeResponse) String 

func (m *LongRunningRecognizeResponse) String() string

type RecognitionAudio 

type RecognitionAudio struct {
	// The audio source, which is either inline content or a Google Cloud
	// Storage uri.
	//
	// Types that are valid to be assigned to AudioSource:
	//	*RecognitionAudio_Content
	//	*RecognitionAudio_Uri
	AudioSource isRecognitionAudio_AudioSource `protobuf_oneof:"audio_source"`
}

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).

func (*RecognitionAudio) Descriptor 

func (*RecognitionAudio) Descriptor() ([]byte, []int)

func (*RecognitionAudio) GetAudioSource 

func (m *RecognitionAudio) GetAudioSource() isRecognitionAudio_AudioSource

func (*RecognitionAudio) GetContent 

func (m *RecognitionAudio) GetContent() []byte

func (*RecognitionAudio) GetUri 

func (m *RecognitionAudio) GetUri() string

func (*RecognitionAudio) ProtoMessage 

func (*RecognitionAudio) ProtoMessage()

func (*RecognitionAudio) Reset 

func (m *RecognitionAudio) Reset()

func (*RecognitionAudio) String 

func (m *RecognitionAudio) String() string

func (*RecognitionAudio) XXX_OneofFuncs 

func (*RecognitionAudio) XXX_OneofFuncs() (func(msg proto.Message, b *proto.Buffer) error, func(msg proto.Message, tag, wire int, b *proto.Buffer) (bool, error), func(msg proto.Message) (n int), []interface{})

XXX_OneofFuncs is for the internal use of the proto package.

type RecognitionAudio_Content 

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

type RecognitionAudio_Uri 

type RecognitionAudio_Uri struct {
	Uri string `protobuf:"bytes,2,opt,name=uri,oneof"`
}

type RecognitionConfig 

type RecognitionConfig struct {
	// *Required* Encoding of audio data sent in all `RecognitionAudio` messages.
	Encoding RecognitionConfig_AudioEncoding `protobuf:"varint,1,opt,name=encoding,enum=google.cloud.speech.v1.RecognitionConfig_AudioEncoding" json:"encoding,omitempty"`
	// *Required* 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).
	SampleRateHertz int32 `protobuf:"varint,2,opt,name=sample_rate_hertz,json=sampleRateHertz" json:"sample_rate_hertz,omitempty"`
	// *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.
	LanguageCode string `protobuf:"bytes,3,opt,name=language_code,json=languageCode" 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`-`30`. A value of `0` or `1` will return a maximum of
	// one. If omitted, will return a maximum of one.
	MaxAlternatives int32 `protobuf:"varint,4,opt,name=max_alternatives,json=maxAlternatives" json:"max_alternatives,omitempty"`
	// *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.
	ProfanityFilter bool `protobuf:"varint,5,opt,name=profanity_filter,json=profanityFilter" 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" 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 `protobuf:"varint,8,opt,name=enable_word_time_offsets,json=enableWordTimeOffsets" json:"enable_word_time_offsets,omitempty"`
}

Provides information to the recognizer that specifies how to process the request.

func (*RecognitionConfig) Descriptor 

func (*RecognitionConfig) Descriptor() ([]byte, []int)

func (*RecognitionConfig) GetEnableWordTimeOffsets 

func (m *RecognitionConfig) GetEnableWordTimeOffsets() bool

func (*RecognitionConfig) GetEncoding 

func (m *RecognitionConfig) GetEncoding() RecognitionConfig_AudioEncoding

func (*RecognitionConfig) GetLanguageCode 

func (m *RecognitionConfig) GetLanguageCode() string

func (*RecognitionConfig) GetMaxAlternatives 

func (m *RecognitionConfig) GetMaxAlternatives() int32

func (*RecognitionConfig) GetProfanityFilter 

func (m *RecognitionConfig) GetProfanityFilter() bool

func (*RecognitionConfig) GetSampleRateHertz 

func (m *RecognitionConfig) GetSampleRateHertz() int32

func (*RecognitionConfig) GetSpeechContexts 

func (m *RecognitionConfig) GetSpeechContexts() []*SpeechContext

func (*RecognitionConfig) ProtoMessage 

func (*RecognitionConfig) ProtoMessage()

func (*RecognitionConfig) Reset 

func (m *RecognitionConfig) Reset()

func (*RecognitionConfig) String 

func (m *RecognitionConfig) String() string

type RecognitionConfig_AudioEncoding 

type RecognitionConfig_AudioEncoding int32

Audio encoding of the data sent in the audio message. All encodings support only 1 channel (mono) audio. Only `FLAC` and `WAV` include a header that describes the bytes of audio that follow the header. The other encodings are raw audio bytes with no header.

For best results, the audio source should be captured and transmitted using a lossless encoding (`FLAC` or `LINEAR16`). Recognition accuracy may be reduced if lossy codecs, which include the other codecs listed in this section, are used to capture or transmit the audio, particularly if background noise is present. 

const (
	// Not specified. Will return result [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
	RecognitionConfig_ENCODING_UNSPECIFIED RecognitionConfig_AudioEncoding = 0
	// Uncompressed 16-bit signed little-endian samples (Linear PCM).
	RecognitionConfig_LINEAR16 RecognitionConfig_AudioEncoding = 1
	// [`FLAC`](https://xiph.org/flac/documentation.html) (Free Lossless Audio
	// Codec) is the recommended encoding because it is
	// lossless--therefore recognition is not compromised--and
	// requires only about half the bandwidth of `LINEAR16`. `FLAC` stream
	// encoding supports 16-bit and 24-bit samples, however, not all fields in
	// `STREAMINFO` are supported.
	RecognitionConfig_FLAC RecognitionConfig_AudioEncoding = 2
	// 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
	RecognitionConfig_MULAW RecognitionConfig_AudioEncoding = 3
	// Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
	RecognitionConfig_AMR RecognitionConfig_AudioEncoding = 4
	// Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
	RecognitionConfig_AMR_WB RecognitionConfig_AudioEncoding = 5
	// Opus encoded audio frames in Ogg container
	// ([OggOpus](https://wiki.xiph.org/OggOpus)).
	// `sample_rate_hertz` must be 16000.
	RecognitionConfig_OGG_OPUS RecognitionConfig_AudioEncoding = 6
	// Although the use of lossy encodings is not recommended, if a very low
	// bitrate encoding is required, `OGG_OPUS` is highly preferred over
	// Speex encoding. The [Speex](https://speex.org/)  encoding supported by
	// Cloud Speech API has a header byte in each block, as in MIME type
	// `audio/x-speex-with-header-byte`.
	// It is a variant of the RTP Speex encoding defined in
	// [RFC 5574](https://tools.ietf.org/html/rfc5574).
	// The stream is a sequence of blocks, one block per RTP packet. Each block
	// starts with a byte containing the length of the block, in bytes, followed
	// by one or more frames of Speex data, padded to an integral number of
	// bytes (octets) as specified in RFC 5574. In other words, each RTP header
	// is replaced with a single byte containing the block length. Only Speex
	// wideband is supported. `sample_rate_hertz` must be 16000.
	RecognitionConfig_SPEEX_WITH_HEADER_BYTE RecognitionConfig_AudioEncoding = 7
)

func (RecognitionConfig_AudioEncoding) EnumDescriptor 

func (RecognitionConfig_AudioEncoding) EnumDescriptor() ([]byte, []int)

func (RecognitionConfig_AudioEncoding) String 

func (x RecognitionConfig_AudioEncoding) String() string

type RecognizeRequest 

type RecognizeRequest struct {
	// *Required* Provides information to the recognizer that specifies how to
	// process the request.
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config" json:"config,omitempty"`
	// *Required* The audio data to be recognized.
	Audio *RecognitionAudio `protobuf:"bytes,2,opt,name=audio" json:"audio,omitempty"`
}

The top-level message sent by the client for the `Recognize` method.

func (*RecognizeRequest) Descriptor 

func (*RecognizeRequest) Descriptor() ([]byte, []int)

func (*RecognizeRequest) GetAudio 

func (m *RecognizeRequest) GetAudio() *RecognitionAudio

func (*RecognizeRequest) GetConfig 

func (m *RecognizeRequest) GetConfig() *RecognitionConfig

func (*RecognizeRequest) ProtoMessage 

func (*RecognizeRequest) ProtoMessage()

func (*RecognizeRequest) Reset 

func (m *RecognizeRequest) Reset()

func (*RecognizeRequest) String 

func (m *RecognizeRequest) String() string

type RecognizeResponse 

type RecognizeResponse struct {
	// *Output-only* Sequential list of transcription results corresponding to
	// sequential portions of audio.
	Results []*SpeechRecognitionResult `protobuf:"bytes,2,rep,name=results" json:"results,omitempty"`
}

The only message returned to the client by the `Recognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages.

func (*RecognizeResponse) Descriptor 

func (*RecognizeResponse) Descriptor() ([]byte, []int)

func (*RecognizeResponse) GetResults 

func (m *RecognizeResponse) GetResults() []*SpeechRecognitionResult

func (*RecognizeResponse) ProtoMessage 

func (*RecognizeResponse) ProtoMessage()

func (*RecognizeResponse) Reset 

func (m *RecognizeResponse) Reset()

func (*RecognizeResponse) String 

func (m *RecognizeResponse) String() string

type SpeechClient 

type SpeechClient 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 the
	// google.longrunning.Operations interface. Returns either an
	// `Operation.error` or an `Operation.response` which contains
	// a `LongRunningRecognizeResponse` message.
	LongRunningRecognize(ctx context.Context, in *LongRunningRecognizeRequest, opts ...grpc.CallOption) (*google_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) (Speech_StreamingRecognizeClient, error)
}

func NewSpeechClient 

func NewSpeechClient(cc *grpc.ClientConn) SpeechClient

type SpeechContext 

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](https://cloud.google.com/speech/limits#content).
	Phrases []string `protobuf:"bytes,1,rep,name=phrases" json:"phrases,omitempty"`
}

Provides "hints" to the speech recognizer to favor specific words and phrases in the results.

func (*SpeechContext) Descriptor 

func (*SpeechContext) Descriptor() ([]byte, []int)

func (*SpeechContext) GetPhrases 

func (m *SpeechContext) GetPhrases() []string

func (*SpeechContext) ProtoMessage 

func (*SpeechContext) ProtoMessage()

func (*SpeechContext) Reset 

func (m *SpeechContext) Reset()

func (*SpeechContext) String 

func (m *SpeechContext) String() string

type SpeechRecognitionAlternative 

type SpeechRecognitionAlternative struct {
	// *Output-only* Transcript text representing the words that the user spoke.
	Transcript string `protobuf:"bytes,1,opt,name=transcript" 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" json:"confidence,omitempty"`
	// *Output-only* A list of word-specific information for each recognized word.
	Words []*WordInfo `protobuf:"bytes,3,rep,name=words" json:"words,omitempty"`
}

Alternative hypotheses (a.k.a. n-best list).

func (*SpeechRecognitionAlternative) Descriptor 

func (*SpeechRecognitionAlternative) Descriptor() ([]byte, []int)

func (*SpeechRecognitionAlternative) GetConfidence 

func (m *SpeechRecognitionAlternative) GetConfidence() float32

func (*SpeechRecognitionAlternative) GetTranscript 

func (m *SpeechRecognitionAlternative) GetTranscript() string

func (*SpeechRecognitionAlternative) GetWords 

func (m *SpeechRecognitionAlternative) GetWords() []*WordInfo

func (*SpeechRecognitionAlternative) ProtoMessage 

func (*SpeechRecognitionAlternative) ProtoMessage()

func (*SpeechRecognitionAlternative) Reset 

func (m *SpeechRecognitionAlternative) Reset()

func (*SpeechRecognitionAlternative) String 

func (m *SpeechRecognitionAlternative) String() string

type SpeechRecognitionResult 

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" json:"alternatives,omitempty"`
}

A speech recognition result corresponding to a portion of the audio.

func (*SpeechRecognitionResult) Descriptor 

func (*SpeechRecognitionResult) Descriptor() ([]byte, []int)

func (*SpeechRecognitionResult) GetAlternatives 

func (m *SpeechRecognitionResult) GetAlternatives() []*SpeechRecognitionAlternative

func (*SpeechRecognitionResult) ProtoMessage 

func (*SpeechRecognitionResult) ProtoMessage()

func (*SpeechRecognitionResult) Reset 

func (m *SpeechRecognitionResult) Reset()

func (*SpeechRecognitionResult) String 

func (m *SpeechRecognitionResult) String() string

type SpeechServer 

type SpeechServer 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 the
	// google.longrunning.Operations interface. Returns either an
	// `Operation.error` or an `Operation.response` which contains
	// a `LongRunningRecognizeResponse` message.
	LongRunningRecognize(context.Context, *LongRunningRecognizeRequest) (*google_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(Speech_StreamingRecognizeServer) error
}

type Speech_StreamingRecognizeClient 

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

type Speech_StreamingRecognizeServer 

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

type StreamingRecognitionConfig 

type StreamingRecognitionConfig struct {
	// *Required* Provides information to the recognizer that specifies how to
	// process the request.
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config" 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" 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" json:"interim_results,omitempty"`
}

Provides information to the recognizer that specifies how to process the request.

func (*StreamingRecognitionConfig) Descriptor 

func (*StreamingRecognitionConfig) Descriptor() ([]byte, []int)

func (*StreamingRecognitionConfig) GetConfig 

func (m *StreamingRecognitionConfig) GetConfig() *RecognitionConfig

func (*StreamingRecognitionConfig) GetInterimResults 

func (m *StreamingRecognitionConfig) GetInterimResults() bool

func (*StreamingRecognitionConfig) GetSingleUtterance 

func (m *StreamingRecognitionConfig) GetSingleUtterance() bool

func (*StreamingRecognitionConfig) ProtoMessage 

func (*StreamingRecognitionConfig) ProtoMessage()

func (*StreamingRecognitionConfig) Reset 

func (m *StreamingRecognitionConfig) Reset()

func (*StreamingRecognitionConfig) String 

func (m *StreamingRecognitionConfig) String() string

type StreamingRecognitionResult 

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" 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" 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" json:"stability,omitempty"`
}

A streaming speech recognition result corresponding to a portion of the audio that is currently being processed.

func (*StreamingRecognitionResult) Descriptor 

func (*StreamingRecognitionResult) Descriptor() ([]byte, []int)

func (*StreamingRecognitionResult) GetAlternatives 

func (m *StreamingRecognitionResult) GetAlternatives() []*SpeechRecognitionAlternative

func (*StreamingRecognitionResult) GetIsFinal 

func (m *StreamingRecognitionResult) GetIsFinal() bool

func (*StreamingRecognitionResult) GetStability 

func (m *StreamingRecognitionResult) GetStability() float32

func (*StreamingRecognitionResult) ProtoMessage 

func (*StreamingRecognitionResult) ProtoMessage()

func (*StreamingRecognitionResult) Reset 

func (m *StreamingRecognitionResult) Reset()

func (*StreamingRecognitionResult) String 

func (m *StreamingRecognitionResult) String() string

type StreamingRecognizeRequest 

type StreamingRecognizeRequest struct {
	// The streaming request, which is either a streaming config or audio content.
	//
	// Types that are valid to be assigned to StreamingRequest:
	//	*StreamingRecognizeRequest_StreamingConfig
	//	*StreamingRecognizeRequest_AudioContent
	StreamingRequest isStreamingRecognizeRequest_StreamingRequest `protobuf_oneof:"streaming_request"`
}

The top-level message sent by the client for the `StreamingRecognize` method. Multiple `StreamingRecognizeRequest` messages are sent. The first message must contain a `streaming_config` message and must not contain `audio` data. All subsequent messages must contain `audio` data and must not contain a `streaming_config` message.

func (*StreamingRecognizeRequest) Descriptor 

func (*StreamingRecognizeRequest) Descriptor() ([]byte, []int)

func (*StreamingRecognizeRequest) GetAudioContent 

func (m *StreamingRecognizeRequest) GetAudioContent() []byte

func (*StreamingRecognizeRequest) GetStreamingConfig 

func (m *StreamingRecognizeRequest) GetStreamingConfig() *StreamingRecognitionConfig

func (*StreamingRecognizeRequest) GetStreamingRequest 

func (m *StreamingRecognizeRequest) GetStreamingRequest() isStreamingRecognizeRequest_StreamingRequest

func (*StreamingRecognizeRequest) ProtoMessage 

func (*StreamingRecognizeRequest) ProtoMessage()

func (*StreamingRecognizeRequest) Reset 

func (m *StreamingRecognizeRequest) Reset()

func (*StreamingRecognizeRequest) String 

func (m *StreamingRecognizeRequest) String() string

func (*StreamingRecognizeRequest) XXX_OneofFuncs 

func (*StreamingRecognizeRequest) XXX_OneofFuncs() (func(msg proto.Message, b *proto.Buffer) error, func(msg proto.Message, tag, wire int, b *proto.Buffer) (bool, error), func(msg proto.Message) (n int), []interface{})

XXX_OneofFuncs is for the internal use of the proto package.

type StreamingRecognizeRequest_AudioContent 

type StreamingRecognizeRequest_AudioContent struct {
	AudioContent []byte `protobuf:"bytes,2,opt,name=audio_content,json=audioContent,proto3,oneof"`
}

type StreamingRecognizeRequest_StreamingConfig 

type StreamingRecognizeRequest_StreamingConfig struct {
	StreamingConfig *StreamingRecognitionConfig `protobuf:"bytes,1,opt,name=streaming_config,json=streamingConfig,oneof"`
}

type StreamingRecognizeResponse 

type StreamingRecognizeResponse struct {
	// *Output-only* If set, returns a [google.rpc.Status][google.rpc.Status] message that
	// specifies the error for the operation.
	Error *google_rpc.Status `protobuf:"bytes,1,opt,name=error" 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 one `is_final=true` result (the newly settled portion),
	// followed by zero or more `is_final=false` results.
	Results []*StreamingRecognitionResult `protobuf:"bytes,2,rep,name=results" json:"results,omitempty"`
	// *Output-only* Indicates the type of speech event.
	SpeechEventType StreamingRecognizeResponse_SpeechEventType `` /* 173-byte string literal not displayed */
}

`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 }

  1. results { alternatives { transcript: "to be" } stability: 0.9 } results { alternatives { transcript: " or not to be" } stability: 0.01 }
  1. 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 }

  1. results { alternatives { transcript: " that is" } stability: 0.9 } results { alternatives { transcript: " the question" } stability: 0.01 }
  1. 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`.

func (*StreamingRecognizeResponse) Descriptor 

func (*StreamingRecognizeResponse) Descriptor() ([]byte, []int)

func (*StreamingRecognizeResponse) GetError 

func (m *StreamingRecognizeResponse) GetError() *google_rpc.Status

func (*StreamingRecognizeResponse) GetResults 

func (m *StreamingRecognizeResponse) GetResults() []*StreamingRecognitionResult

func (*StreamingRecognizeResponse) GetSpeechEventType 

func (m *StreamingRecognizeResponse) GetSpeechEventType() StreamingRecognizeResponse_SpeechEventType

func (*StreamingRecognizeResponse) ProtoMessage 

func (*StreamingRecognizeResponse) ProtoMessage()

func (*StreamingRecognizeResponse) Reset 

func (m *StreamingRecognizeResponse) Reset()

func (*StreamingRecognizeResponse) String 

func (m *StreamingRecognizeResponse) String() string

type StreamingRecognizeResponse_SpeechEventType 

type StreamingRecognizeResponse_SpeechEventType int32

Indicates the type of speech event. 

const (
	// No speech event specified.
	StreamingRecognizeResponse_SPEECH_EVENT_UNSPECIFIED StreamingRecognizeResponse_SpeechEventType = 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.
	StreamingRecognizeResponse_END_OF_SINGLE_UTTERANCE StreamingRecognizeResponse_SpeechEventType = 1
)

func (StreamingRecognizeResponse_SpeechEventType) EnumDescriptor 

func (StreamingRecognizeResponse_SpeechEventType) EnumDescriptor() ([]byte, []int)

func (StreamingRecognizeResponse_SpeechEventType) String 

func (x StreamingRecognizeResponse_SpeechEventType) String() string

type WordInfo 

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 *google_protobuf3.Duration `protobuf:"bytes,1,opt,name=start_time,json=startTime" 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 *google_protobuf3.Duration `protobuf:"bytes,2,opt,name=end_time,json=endTime" json:"end_time,omitempty"`
	// *Output-only* The word corresponding to this set of information.
	Word string `protobuf:"bytes,3,opt,name=word" json:"word,omitempty"`
}

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`.

func (*WordInfo) Descriptor 

func (*WordInfo) Descriptor() ([]byte, []int)

func (*WordInfo) GetEndTime 

func (m *WordInfo) GetEndTime() *google_protobuf3.Duration

func (*WordInfo) GetStartTime 

func (m *WordInfo) GetStartTime() *google_protobuf3.Duration

func (*WordInfo) GetWord 

func (m *WordInfo) GetWord() string

func (*WordInfo) ProtoMessage 

func (*WordInfo) ProtoMessage()

func (*WordInfo) Reset 

func (m *WordInfo) Reset()

func (*WordInfo) String 

func (m *WordInfo) String() string

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.