Documentation ¶
Index ¶
- Variables
- func RegisterSpeechServer(s *grpc.Server, srv SpeechServer)
- type LongRunningRecognizeMetadata
- func (*LongRunningRecognizeMetadata) Descriptor() ([]byte, []int)
- func (m *LongRunningRecognizeMetadata) GetLastUpdateTime() *timestamp.Timestamp
- func (m *LongRunningRecognizeMetadata) GetProgressPercent() int32
- func (m *LongRunningRecognizeMetadata) GetStartTime() *timestamp.Timestamp
- func (*LongRunningRecognizeMetadata) ProtoMessage()
- func (m *LongRunningRecognizeMetadata) Reset()
- func (m *LongRunningRecognizeMetadata) String() string
- func (m *LongRunningRecognizeMetadata) XXX_DiscardUnknown()
- func (m *LongRunningRecognizeMetadata) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *LongRunningRecognizeMetadata) XXX_Merge(src proto.Message)
- func (m *LongRunningRecognizeMetadata) XXX_Size() int
- func (m *LongRunningRecognizeMetadata) XXX_Unmarshal(b []byte) error
- type LongRunningRecognizeRequest
- func (*LongRunningRecognizeRequest) Descriptor() ([]byte, []int)
- func (m *LongRunningRecognizeRequest) GetAudio() *RecognitionAudio
- func (m *LongRunningRecognizeRequest) GetConfig() *RecognitionConfig
- func (*LongRunningRecognizeRequest) ProtoMessage()
- func (m *LongRunningRecognizeRequest) Reset()
- func (m *LongRunningRecognizeRequest) String() string
- func (m *LongRunningRecognizeRequest) XXX_DiscardUnknown()
- func (m *LongRunningRecognizeRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *LongRunningRecognizeRequest) XXX_Merge(src proto.Message)
- func (m *LongRunningRecognizeRequest) XXX_Size() int
- func (m *LongRunningRecognizeRequest) XXX_Unmarshal(b []byte) error
- type LongRunningRecognizeResponse
- func (*LongRunningRecognizeResponse) Descriptor() ([]byte, []int)
- func (m *LongRunningRecognizeResponse) GetResults() []*SpeechRecognitionResult
- func (*LongRunningRecognizeResponse) ProtoMessage()
- func (m *LongRunningRecognizeResponse) Reset()
- func (m *LongRunningRecognizeResponse) String() string
- func (m *LongRunningRecognizeResponse) XXX_DiscardUnknown()
- func (m *LongRunningRecognizeResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *LongRunningRecognizeResponse) XXX_Merge(src proto.Message)
- func (m *LongRunningRecognizeResponse) XXX_Size() int
- func (m *LongRunningRecognizeResponse) XXX_Unmarshal(b []byte) error
- type RecognitionAudio
- func (*RecognitionAudio) Descriptor() ([]byte, []int)
- func (m *RecognitionAudio) GetAudioSource() isRecognitionAudio_AudioSource
- func (m *RecognitionAudio) GetContent() []byte
- func (m *RecognitionAudio) GetUri() string
- func (*RecognitionAudio) ProtoMessage()
- func (m *RecognitionAudio) Reset()
- func (m *RecognitionAudio) String() string
- func (m *RecognitionAudio) XXX_DiscardUnknown()
- func (m *RecognitionAudio) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *RecognitionAudio) XXX_Merge(src proto.Message)
- func (*RecognitionAudio) XXX_OneofFuncs() (func(msg proto.Message, b *proto.Buffer) error, ...)
- func (m *RecognitionAudio) XXX_Size() int
- func (m *RecognitionAudio) XXX_Unmarshal(b []byte) error
- type RecognitionAudio_Content
- type RecognitionAudio_Uri
- type RecognitionConfig
- func (*RecognitionConfig) Descriptor() ([]byte, []int)
- func (m *RecognitionConfig) GetEnableAutomaticPunctuation() bool
- func (m *RecognitionConfig) GetEnableWordTimeOffsets() bool
- func (m *RecognitionConfig) GetEncoding() RecognitionConfig_AudioEncoding
- func (m *RecognitionConfig) GetLanguageCode() string
- func (m *RecognitionConfig) GetMaxAlternatives() int32
- func (m *RecognitionConfig) GetModel() string
- func (m *RecognitionConfig) GetProfanityFilter() bool
- func (m *RecognitionConfig) GetSampleRateHertz() int32
- func (m *RecognitionConfig) GetSpeechContexts() []*SpeechContext
- func (m *RecognitionConfig) GetUseEnhanced() bool
- func (*RecognitionConfig) ProtoMessage()
- func (m *RecognitionConfig) Reset()
- func (m *RecognitionConfig) String() string
- func (m *RecognitionConfig) XXX_DiscardUnknown()
- func (m *RecognitionConfig) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *RecognitionConfig) XXX_Merge(src proto.Message)
- func (m *RecognitionConfig) XXX_Size() int
- func (m *RecognitionConfig) XXX_Unmarshal(b []byte) error
- type RecognitionConfig_AudioEncoding
- type RecognizeRequest
- func (*RecognizeRequest) Descriptor() ([]byte, []int)
- func (m *RecognizeRequest) GetAudio() *RecognitionAudio
- func (m *RecognizeRequest) GetConfig() *RecognitionConfig
- func (*RecognizeRequest) ProtoMessage()
- func (m *RecognizeRequest) Reset()
- func (m *RecognizeRequest) String() string
- func (m *RecognizeRequest) XXX_DiscardUnknown()
- func (m *RecognizeRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *RecognizeRequest) XXX_Merge(src proto.Message)
- func (m *RecognizeRequest) XXX_Size() int
- func (m *RecognizeRequest) XXX_Unmarshal(b []byte) error
- type RecognizeResponse
- func (*RecognizeResponse) Descriptor() ([]byte, []int)
- func (m *RecognizeResponse) GetResults() []*SpeechRecognitionResult
- func (*RecognizeResponse) ProtoMessage()
- func (m *RecognizeResponse) Reset()
- func (m *RecognizeResponse) String() string
- func (m *RecognizeResponse) XXX_DiscardUnknown()
- func (m *RecognizeResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *RecognizeResponse) XXX_Merge(src proto.Message)
- func (m *RecognizeResponse) XXX_Size() int
- func (m *RecognizeResponse) XXX_Unmarshal(b []byte) error
- type SpeechClient
- type SpeechContext
- func (*SpeechContext) Descriptor() ([]byte, []int)
- func (m *SpeechContext) GetPhrases() []string
- func (*SpeechContext) ProtoMessage()
- func (m *SpeechContext) Reset()
- func (m *SpeechContext) String() string
- func (m *SpeechContext) XXX_DiscardUnknown()
- func (m *SpeechContext) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *SpeechContext) XXX_Merge(src proto.Message)
- func (m *SpeechContext) XXX_Size() int
- func (m *SpeechContext) XXX_Unmarshal(b []byte) error
- type SpeechRecognitionAlternative
- func (*SpeechRecognitionAlternative) Descriptor() ([]byte, []int)
- func (m *SpeechRecognitionAlternative) GetConfidence() float32
- func (m *SpeechRecognitionAlternative) GetTranscript() string
- func (m *SpeechRecognitionAlternative) GetWords() []*WordInfo
- func (*SpeechRecognitionAlternative) ProtoMessage()
- func (m *SpeechRecognitionAlternative) Reset()
- func (m *SpeechRecognitionAlternative) String() string
- func (m *SpeechRecognitionAlternative) XXX_DiscardUnknown()
- func (m *SpeechRecognitionAlternative) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *SpeechRecognitionAlternative) XXX_Merge(src proto.Message)
- func (m *SpeechRecognitionAlternative) XXX_Size() int
- func (m *SpeechRecognitionAlternative) XXX_Unmarshal(b []byte) error
- type SpeechRecognitionResult
- func (*SpeechRecognitionResult) Descriptor() ([]byte, []int)
- func (m *SpeechRecognitionResult) GetAlternatives() []*SpeechRecognitionAlternative
- func (*SpeechRecognitionResult) ProtoMessage()
- func (m *SpeechRecognitionResult) Reset()
- func (m *SpeechRecognitionResult) String() string
- func (m *SpeechRecognitionResult) XXX_DiscardUnknown()
- func (m *SpeechRecognitionResult) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *SpeechRecognitionResult) XXX_Merge(src proto.Message)
- func (m *SpeechRecognitionResult) XXX_Size() int
- func (m *SpeechRecognitionResult) XXX_Unmarshal(b []byte) error
- type SpeechServer
- type Speech_StreamingRecognizeClient
- type Speech_StreamingRecognizeServer
- type StreamingRecognitionConfig
- func (*StreamingRecognitionConfig) Descriptor() ([]byte, []int)
- func (m *StreamingRecognitionConfig) GetConfig() *RecognitionConfig
- func (m *StreamingRecognitionConfig) GetInterimResults() bool
- func (m *StreamingRecognitionConfig) GetSingleUtterance() bool
- func (*StreamingRecognitionConfig) ProtoMessage()
- func (m *StreamingRecognitionConfig) Reset()
- func (m *StreamingRecognitionConfig) String() string
- func (m *StreamingRecognitionConfig) XXX_DiscardUnknown()
- func (m *StreamingRecognitionConfig) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *StreamingRecognitionConfig) XXX_Merge(src proto.Message)
- func (m *StreamingRecognitionConfig) XXX_Size() int
- func (m *StreamingRecognitionConfig) XXX_Unmarshal(b []byte) error
- type StreamingRecognitionResult
- func (*StreamingRecognitionResult) Descriptor() ([]byte, []int)
- func (m *StreamingRecognitionResult) GetAlternatives() []*SpeechRecognitionAlternative
- func (m *StreamingRecognitionResult) GetIsFinal() bool
- func (m *StreamingRecognitionResult) GetStability() float32
- func (*StreamingRecognitionResult) ProtoMessage()
- func (m *StreamingRecognitionResult) Reset()
- func (m *StreamingRecognitionResult) String() string
- func (m *StreamingRecognitionResult) XXX_DiscardUnknown()
- func (m *StreamingRecognitionResult) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *StreamingRecognitionResult) XXX_Merge(src proto.Message)
- func (m *StreamingRecognitionResult) XXX_Size() int
- func (m *StreamingRecognitionResult) XXX_Unmarshal(b []byte) error
- type StreamingRecognizeRequest
- func (*StreamingRecognizeRequest) Descriptor() ([]byte, []int)
- func (m *StreamingRecognizeRequest) GetAudioContent() []byte
- func (m *StreamingRecognizeRequest) GetStreamingConfig() *StreamingRecognitionConfig
- func (m *StreamingRecognizeRequest) GetStreamingRequest() isStreamingRecognizeRequest_StreamingRequest
- func (*StreamingRecognizeRequest) ProtoMessage()
- func (m *StreamingRecognizeRequest) Reset()
- func (m *StreamingRecognizeRequest) String() string
- func (m *StreamingRecognizeRequest) XXX_DiscardUnknown()
- func (m *StreamingRecognizeRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *StreamingRecognizeRequest) XXX_Merge(src proto.Message)
- func (*StreamingRecognizeRequest) XXX_OneofFuncs() (func(msg proto.Message, b *proto.Buffer) error, ...)
- func (m *StreamingRecognizeRequest) XXX_Size() int
- func (m *StreamingRecognizeRequest) XXX_Unmarshal(b []byte) error
- type StreamingRecognizeRequest_AudioContent
- type StreamingRecognizeRequest_StreamingConfig
- type StreamingRecognizeResponse
- func (*StreamingRecognizeResponse) Descriptor() ([]byte, []int)
- func (m *StreamingRecognizeResponse) GetError() *status.Status
- func (m *StreamingRecognizeResponse) GetResults() []*StreamingRecognitionResult
- func (m *StreamingRecognizeResponse) GetSpeechEventType() StreamingRecognizeResponse_SpeechEventType
- func (*StreamingRecognizeResponse) ProtoMessage()
- func (m *StreamingRecognizeResponse) Reset()
- func (m *StreamingRecognizeResponse) String() string
- func (m *StreamingRecognizeResponse) XXX_DiscardUnknown()
- func (m *StreamingRecognizeResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *StreamingRecognizeResponse) XXX_Merge(src proto.Message)
- func (m *StreamingRecognizeResponse) XXX_Size() int
- func (m *StreamingRecognizeResponse) XXX_Unmarshal(b []byte) error
- type StreamingRecognizeResponse_SpeechEventType
- type WordInfo
- func (*WordInfo) Descriptor() ([]byte, []int)
- func (m *WordInfo) GetEndTime() *duration.Duration
- func (m *WordInfo) GetStartTime() *duration.Duration
- func (m *WordInfo) GetWord() string
- func (*WordInfo) ProtoMessage()
- func (m *WordInfo) Reset()
- func (m *WordInfo) String() string
- func (m *WordInfo) XXX_DiscardUnknown()
- func (m *WordInfo) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
- func (m *WordInfo) XXX_Merge(src proto.Message)
- func (m *WordInfo) XXX_Size() int
- func (m *WordInfo) XXX_Unmarshal(b []byte) error
Constants ¶
This section is empty.
Variables ¶
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",
}
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,
}
var StreamingRecognizeResponse_SpeechEventType_name = map[int32]string{
0: "SPEECH_EVENT_UNSPECIFIED",
1: "END_OF_SINGLE_UTTERANCE",
}
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,proto3" json:"progress_percent,omitempty"` // Time when the request was received. StartTime *timestamp.Timestamp `protobuf:"bytes,2,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"` // Time of the most recent processing update. LastUpdateTime *timestamp.Timestamp `protobuf:"bytes,3,opt,name=last_update_time,json=lastUpdateTime,proto3" json:"last_update_time,omitempty"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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() *timestamp.Timestamp
func (*LongRunningRecognizeMetadata) GetProgressPercent ¶
func (m *LongRunningRecognizeMetadata) GetProgressPercent() int32
func (*LongRunningRecognizeMetadata) GetStartTime ¶
func (m *LongRunningRecognizeMetadata) GetStartTime() *timestamp.Timestamp
func (*LongRunningRecognizeMetadata) ProtoMessage ¶
func (*LongRunningRecognizeMetadata) ProtoMessage()
func (*LongRunningRecognizeMetadata) Reset ¶
func (m *LongRunningRecognizeMetadata) Reset()
func (*LongRunningRecognizeMetadata) String ¶
func (m *LongRunningRecognizeMetadata) String() string
func (*LongRunningRecognizeMetadata) XXX_DiscardUnknown ¶
func (m *LongRunningRecognizeMetadata) XXX_DiscardUnknown()
func (*LongRunningRecognizeMetadata) XXX_Marshal ¶
func (m *LongRunningRecognizeMetadata) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*LongRunningRecognizeMetadata) XXX_Merge ¶
func (m *LongRunningRecognizeMetadata) XXX_Merge(src proto.Message)
func (*LongRunningRecognizeMetadata) XXX_Size ¶
func (m *LongRunningRecognizeMetadata) XXX_Size() int
func (*LongRunningRecognizeMetadata) XXX_Unmarshal ¶
func (m *LongRunningRecognizeMetadata) XXX_Unmarshal(b []byte) error
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,proto3" json:"config,omitempty"` // *Required* The audio data to be recognized. Audio *RecognitionAudio `protobuf:"bytes,2,opt,name=audio,proto3" json:"audio,omitempty"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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
func (*LongRunningRecognizeRequest) XXX_DiscardUnknown ¶
func (m *LongRunningRecognizeRequest) XXX_DiscardUnknown()
func (*LongRunningRecognizeRequest) XXX_Marshal ¶
func (m *LongRunningRecognizeRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*LongRunningRecognizeRequest) XXX_Merge ¶
func (m *LongRunningRecognizeRequest) XXX_Merge(src proto.Message)
func (*LongRunningRecognizeRequest) XXX_Size ¶
func (m *LongRunningRecognizeRequest) XXX_Size() int
func (*LongRunningRecognizeRequest) XXX_Unmarshal ¶
func (m *LongRunningRecognizeRequest) XXX_Unmarshal(b []byte) error
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,proto3" json:"results,omitempty"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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
func (*LongRunningRecognizeResponse) XXX_DiscardUnknown ¶
func (m *LongRunningRecognizeResponse) XXX_DiscardUnknown()
func (*LongRunningRecognizeResponse) XXX_Marshal ¶
func (m *LongRunningRecognizeResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*LongRunningRecognizeResponse) XXX_Merge ¶
func (m *LongRunningRecognizeResponse) XXX_Merge(src proto.Message)
func (*LongRunningRecognizeResponse) XXX_Size ¶
func (m *LongRunningRecognizeResponse) XXX_Size() int
func (*LongRunningRecognizeResponse) XXX_Unmarshal ¶
func (m *LongRunningRecognizeResponse) XXX_Unmarshal(b []byte) error
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"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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 [content limits](/speech-to-text/quotas#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_DiscardUnknown ¶
func (m *RecognitionAudio) XXX_DiscardUnknown()
func (*RecognitionAudio) XXX_Marshal ¶
func (m *RecognitionAudio) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*RecognitionAudio) XXX_Merge ¶
func (m *RecognitionAudio) XXX_Merge(src proto.Message)
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.
func (*RecognitionAudio) XXX_Size ¶
func (m *RecognitionAudio) XXX_Size() int
func (*RecognitionAudio) XXX_Unmarshal ¶
func (m *RecognitionAudio) XXX_Unmarshal(b []byte) error
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,proto3,oneof"`
}
type RecognitionConfig ¶
type RecognitionConfig struct { // Encoding of audio data sent in all `RecognitionAudio` messages. // This field is optional for `FLAC` and `WAV` audio files and required // for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding]. Encoding RecognitionConfig_AudioEncoding `` /* 130-byte string literal not displayed */ // 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). // This field is optional for `FLAC` and `WAV` audio files and required // for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding]. SampleRateHertz int32 `protobuf:"varint,2,opt,name=sample_rate_hertz,json=sampleRateHertz,proto3" 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](/speech-to-text/docs/languages) // 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`-`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,proto3" 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,proto3" json:"profanity_filter,omitempty"` // *Optional* array of [SpeechContext][google.cloud.speech.v1.SpeechContext]. // A means to provide context to assist the speech recognition. For more // information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints). 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* If 'true', adds punctuation to recognition result hypotheses. // This feature is only available in select languages. Setting this for // requests in other languages has no effect at all. // The default 'false' value does not add punctuation to result hypotheses. // Note: This is currently offered as an experimental service, complimentary // to all users. In the future this may be exclusively available as a // premium feature. EnableAutomaticPunctuation bool `` /* 143-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, then we auto-select a model based on the parameters // in the RecognitionConfig. // <table> // <tr> // <td><b>Model</b></td> // <td><b>Description</b></td> // </tr> // <tr> // <td><code>command_and_search</code></td> // <td>Best for short queries such as voice commands or voice search.</td> // </tr> // <tr> // <td><code>phone_call</code></td> // <td>Best for audio that originated from a phone call (typically // recorded at an 8khz sampling rate).</td> // </tr> // <tr> // <td><code>video</code></td> // <td>Best for audio that originated from from video or includes multiple // speakers. Ideally the audio is recorded at a 16khz or greater // sampling rate. This is a premium model that costs more than the // standard rate.</td> // </tr> // <tr> // <td><code>default</code></td> // <td>Best for audio that is not one of the specific audio models. // For example, long-form audio. Ideally the audio is high-fidelity, // recorded at a 16khz or greater sampling rate.</td> // </tr> // </table> Model string `protobuf:"bytes,13,opt,name=model,proto3" json:"model,omitempty"` // *Optional* Set to true to use an enhanced model for speech recognition. // You must also set the `model` field to a valid, enhanced model. If // `use_enhanced` is set to true and the `model` field is not set, then // `use_enhanced` is ignored. If `use_enhanced` is true and an enhanced // version of the specified model does not exist, then the speech is // recognized using the standard version of the specified model. // // Enhanced speech models require that you opt-in to data logging using // instructions in the [documentation](/speech-to-text/enable-data-logging). // If you set `use_enhanced` to true and you have not enabled audio logging, // then you will receive an error. UseEnhanced bool `protobuf:"varint,14,opt,name=use_enhanced,json=useEnhanced,proto3" json:"use_enhanced,omitempty"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
Provides information to the recognizer that specifies how to process the request.
func (*RecognitionConfig) Descriptor ¶
func (*RecognitionConfig) Descriptor() ([]byte, []int)
func (*RecognitionConfig) GetEnableAutomaticPunctuation ¶
func (m *RecognitionConfig) GetEnableAutomaticPunctuation() bool
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) GetModel ¶
func (m *RecognitionConfig) GetModel() string
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) GetUseEnhanced ¶
func (m *RecognitionConfig) GetUseEnhanced() bool
func (*RecognitionConfig) ProtoMessage ¶
func (*RecognitionConfig) ProtoMessage()
func (*RecognitionConfig) Reset ¶
func (m *RecognitionConfig) Reset()
func (*RecognitionConfig) String ¶
func (m *RecognitionConfig) String() string
func (*RecognitionConfig) XXX_DiscardUnknown ¶
func (m *RecognitionConfig) XXX_DiscardUnknown()
func (*RecognitionConfig) XXX_Marshal ¶
func (m *RecognitionConfig) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*RecognitionConfig) XXX_Merge ¶
func (m *RecognitionConfig) XXX_Merge(src proto.Message)
func (*RecognitionConfig) XXX_Size ¶
func (m *RecognitionConfig) XXX_Size() int
func (*RecognitionConfig) XXX_Unmarshal ¶
func (m *RecognitionConfig) XXX_Unmarshal(b []byte) error
type RecognitionConfig_AudioEncoding ¶
type RecognitionConfig_AudioEncoding int32
The encoding of the audio data sent in the request.
All encodings support only 1 channel (mono) audio.
For best results, the audio source should be captured and transmitted using a lossless encoding (`FLAC` or `LINEAR16`). The accuracy of the speech recognition can be reduced if lossy codecs are used to capture or transmit audio, particularly if background noise is present. Lossy codecs include `MULAW`, `AMR`, `AMR_WB`, `OGG_OPUS`, and `SPEEX_WITH_HEADER_BYTE`.
The `FLAC` and `WAV` audio file formats include a header that describes the included audio content. You can request recognition for `WAV` files that contain either `LINEAR16` or `MULAW` encoded audio. If you send `FLAC` or `WAV` audio file format in your request, you do not need to specify an `AudioEncoding`; the audio encoding format is determined from the file header. If you specify an `AudioEncoding` when you send send `FLAC` or `WAV` audio, the encoding configuration must match the encoding described in the audio header; otherwise the request returns an [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error code.
const ( // Not specified. RecognitionConfig_ENCODING_UNSPECIFIED RecognitionConfig_AudioEncoding = 0 // Uncompressed 16-bit signed little-endian samples (Linear PCM). RecognitionConfig_LINEAR16 RecognitionConfig_AudioEncoding = 1 // `FLAC` (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 one of 8000, 12000, 16000, 24000, or 48000. 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,proto3" json:"config,omitempty"` // *Required* The audio data to be recognized. Audio *RecognitionAudio `protobuf:"bytes,2,opt,name=audio,proto3" json:"audio,omitempty"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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
func (*RecognizeRequest) XXX_DiscardUnknown ¶
func (m *RecognizeRequest) XXX_DiscardUnknown()
func (*RecognizeRequest) XXX_Marshal ¶
func (m *RecognizeRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*RecognizeRequest) XXX_Merge ¶
func (m *RecognizeRequest) XXX_Merge(src proto.Message)
func (*RecognizeRequest) XXX_Size ¶
func (m *RecognizeRequest) XXX_Size() int
func (*RecognizeRequest) XXX_Unmarshal ¶
func (m *RecognizeRequest) XXX_Unmarshal(b []byte) error
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,proto3" json:"results,omitempty"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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
func (*RecognizeResponse) XXX_DiscardUnknown ¶
func (m *RecognizeResponse) XXX_DiscardUnknown()
func (*RecognizeResponse) XXX_Marshal ¶
func (m *RecognizeResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*RecognizeResponse) XXX_Merge ¶
func (m *RecognizeResponse) XXX_Merge(src proto.Message)
func (*RecognizeResponse) XXX_Size ¶
func (m *RecognizeResponse) XXX_Size() int
func (*RecognizeResponse) XXX_Unmarshal ¶
func (m *RecognizeResponse) XXX_Unmarshal(b []byte) error
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) (*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) }
SpeechClient is the client API for Speech service.
For semantics around ctx use and closing/ending streaming RPCs, please refer to https://godoc.org/google.golang.org/grpc#ClientConn.NewStream.
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](/speech-to-text/quotas#content). Phrases []string `protobuf:"bytes,1,rep,name=phrases,proto3" json:"phrases,omitempty"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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
func (*SpeechContext) XXX_DiscardUnknown ¶
func (m *SpeechContext) XXX_DiscardUnknown()
func (*SpeechContext) XXX_Marshal ¶
func (m *SpeechContext) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*SpeechContext) XXX_Merge ¶
func (m *SpeechContext) XXX_Merge(src proto.Message)
func (*SpeechContext) XXX_Size ¶
func (m *SpeechContext) XXX_Size() int
func (*SpeechContext) XXX_Unmarshal ¶
func (m *SpeechContext) XXX_Unmarshal(b []byte) error
type SpeechRecognitionAlternative ¶
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 set only for the top alternative of a non-streaming // result or, of a streaming result where `is_final=true`. // This field is not guaranteed to be accurate and users should not rely on it // to be always provided. // The default of 0.0 is a sentinel value indicating `confidence` was not set. 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"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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
func (*SpeechRecognitionAlternative) XXX_DiscardUnknown ¶
func (m *SpeechRecognitionAlternative) XXX_DiscardUnknown()
func (*SpeechRecognitionAlternative) XXX_Marshal ¶
func (m *SpeechRecognitionAlternative) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*SpeechRecognitionAlternative) XXX_Merge ¶
func (m *SpeechRecognitionAlternative) XXX_Merge(src proto.Message)
func (*SpeechRecognitionAlternative) XXX_Size ¶
func (m *SpeechRecognitionAlternative) XXX_Size() int
func (*SpeechRecognitionAlternative) XXX_Unmarshal ¶
func (m *SpeechRecognitionAlternative) XXX_Unmarshal(b []byte) error
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,proto3" json:"alternatives,omitempty"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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
func (*SpeechRecognitionResult) XXX_DiscardUnknown ¶
func (m *SpeechRecognitionResult) XXX_DiscardUnknown()
func (*SpeechRecognitionResult) XXX_Marshal ¶
func (m *SpeechRecognitionResult) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*SpeechRecognitionResult) XXX_Merge ¶
func (m *SpeechRecognitionResult) XXX_Merge(src proto.Message)
func (*SpeechRecognitionResult) XXX_Size ¶
func (m *SpeechRecognitionResult) XXX_Size() int
func (*SpeechRecognitionResult) XXX_Unmarshal ¶
func (m *SpeechRecognitionResult) XXX_Unmarshal(b []byte) error
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) (*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 }
SpeechServer is the server API for Speech service.
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,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"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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
func (*StreamingRecognitionConfig) XXX_DiscardUnknown ¶
func (m *StreamingRecognitionConfig) XXX_DiscardUnknown()
func (*StreamingRecognitionConfig) XXX_Marshal ¶
func (m *StreamingRecognitionConfig) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*StreamingRecognitionConfig) XXX_Merge ¶
func (m *StreamingRecognitionConfig) XXX_Merge(src proto.Message)
func (*StreamingRecognitionConfig) XXX_Size ¶
func (m *StreamingRecognitionConfig) XXX_Size() int
func (*StreamingRecognitionConfig) XXX_Unmarshal ¶
func (m *StreamingRecognitionConfig) XXX_Unmarshal(b []byte) error
type StreamingRecognitionResult ¶
type StreamingRecognitionResult 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"` // 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"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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
func (*StreamingRecognitionResult) XXX_DiscardUnknown ¶
func (m *StreamingRecognitionResult) XXX_DiscardUnknown()
func (*StreamingRecognitionResult) XXX_Marshal ¶
func (m *StreamingRecognitionResult) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*StreamingRecognitionResult) XXX_Merge ¶
func (m *StreamingRecognitionResult) XXX_Merge(src proto.Message)
func (*StreamingRecognitionResult) XXX_Size ¶
func (m *StreamingRecognitionResult) XXX_Size() int
func (*StreamingRecognitionResult) XXX_Unmarshal ¶
func (m *StreamingRecognitionResult) XXX_Unmarshal(b []byte) error
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"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
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_DiscardUnknown ¶
func (m *StreamingRecognizeRequest) XXX_DiscardUnknown()
func (*StreamingRecognizeRequest) XXX_Marshal ¶
func (m *StreamingRecognizeRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*StreamingRecognizeRequest) XXX_Merge ¶
func (m *StreamingRecognizeRequest) XXX_Merge(src proto.Message)
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.
func (*StreamingRecognizeRequest) XXX_Size ¶
func (m *StreamingRecognizeRequest) XXX_Size() int
func (*StreamingRecognizeRequest) XXX_Unmarshal ¶
func (m *StreamingRecognizeRequest) XXX_Unmarshal(b []byte) error
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,proto3,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 *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 one `is_final=true` result (the newly settled portion), // followed by zero or more `is_final=false` results (the interim results). Results []*StreamingRecognitionResult `protobuf:"bytes,2,rep,name=results,proto3" json:"results,omitempty"` // Output only. Indicates the type of speech event. SpeechEventType StreamingRecognizeResponse_SpeechEventType `` /* 180-byte string literal not displayed */ XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
`StreamingRecognizeResponse` is the only message returned to the client by `StreamingRecognize`. A series of zero or more `StreamingRecognizeResponse` messages are streamed back to the client. If there is no recognizable audio, and `single_utterance` is set to false, then no 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 }
- results { alternatives { transcript: "to be" } stability: 0.9 } results { alternatives { transcript: " or not to be" } stability: 0.01 }
- 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 }
- results { alternatives { transcript: " that is" } stability: 0.9 } results { alternatives { transcript: " the question" } stability: 0.01 }
- 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() *status.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
func (*StreamingRecognizeResponse) XXX_DiscardUnknown ¶
func (m *StreamingRecognizeResponse) XXX_DiscardUnknown()
func (*StreamingRecognizeResponse) XXX_Marshal ¶
func (m *StreamingRecognizeResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)
func (*StreamingRecognizeResponse) XXX_Merge ¶
func (m *StreamingRecognizeResponse) XXX_Merge(src proto.Message)
func (*StreamingRecognizeResponse) XXX_Size ¶
func (m *StreamingRecognizeResponse) XXX_Size() int
func (*StreamingRecognizeResponse) XXX_Unmarshal ¶
func (m *StreamingRecognizeResponse) XXX_Unmarshal(b []byte) error
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 *duration.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 *duration.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"` XXX_NoUnkeyedLiteral struct{} `json:"-"` XXX_unrecognized []byte `json:"-"` XXX_sizecache int32 `json:"-"` }
Word-specific information for recognized words.
func (*WordInfo) Descriptor ¶
func (*WordInfo) GetEndTime ¶
func (*WordInfo) GetStartTime ¶
func (*WordInfo) ProtoMessage ¶
func (*WordInfo) ProtoMessage()
func (*WordInfo) XXX_DiscardUnknown ¶
func (m *WordInfo) XXX_DiscardUnknown()