asr

package
v1.0.17 Latest Latest
Warning

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

 Go to latest Published: Jun 4, 2025 License: Apache-2.0 Imports: 18 Imported by: 2

Documentation

Index

Constants

View Source 
const (
	AudioFormatPCM   = 1
	AudioFormatSpeex = 4
	AudioFormatSilk  = 6
	AudioFormatMp3   = 8
	AudioFormatOpus  = 10
	AudioFormatWav   = 12
	AudioFormatM4A   = 14
	AudioFormatAAC   = 16
)

AudioFormat type

Variables

This section is empty.

Functions

This section is empty.

Types

type FlashRecognitionRequest added in v1.0.3 

type FlashRecognitionRequest struct {
	EngineType         string `json:"engine_type"`
	VoiceFormat        string `json:"voice_format"`
	SpeakerDiarization uint32 `json:"speaker_diarization"`
	HotwordId          string `json:"hotword_id"`
	HotwordList        string `json:"hotword_list"`
	CustomizationId    string `json:"customization_id"`
	FilterDirty        int32  `json:"filter_dirty"`
	FilterModal        int32  `json:"filter_modal"`
	FilterPunc         int32  `json:"filter_punc"`
	ConvertNumMode     int32  `json:"convert_num_mode"`
	WordInfo           int32  `json:"word_info"`
	FirstChannelOnly   int32  `json:"first_channel_only"`
	ReinforceHotword   int32  `json:"reinforce_hotword"`
	SentenceMaxLength  int32  `json:"sentence_max_length"`
}

FlashRecognitionRequest FlashRecognitionRequest

type FlashRecognitionResponse added in v1.0.3 

type FlashRecognitionResponse struct {
	RequestId     string                    `json:"request_id"`
	Code          int                       `json:"code"`
	Message       string                    `json:"message"`
	AudioDuration int64                     `json:"audio_duration"`
	FlashResult   []*FlashRecognitionResult `json:"flash_result,omitempty"`
}

FlashRecognitionResponse FlashRecognitionResponse

type FlashRecognitionResult added in v1.0.3 

type FlashRecognitionResult struct {
	Text         string                      `json:"text"`
	ChannelId    int32                       `json:"channel_id"`
	SentenceList []*FlashRecognitionSentence `json:"sentence_list,omitempty"`
}

FlashRecognitionResult FlashRecognitionResult

type FlashRecognitionSentence added in v1.0.3 

type FlashRecognitionSentence struct {
	Text      string           `json:"text"`
	StartTime uint32           `json:"start_time"`
	EndTime   uint32           `json:"end_time"`
	SpeakerId int32            `json:"speaker_id"`
	WordList  []*FlashWordData `json:"word_list,omitempty"`
}

FlashRecognitionSentence FlashRecognitionSentence

type FlashRecognizer added in v1.0.3 

type FlashRecognizer struct {
	AppID string

	//for proxy
	ProxyURL string

	Credential *common.Credential
}

FlashRecognizer is the entry for ASR flash recognizer

func NewFlashRecognizer added in v1.0.3 

func NewFlashRecognizer(appID string, credential *common.Credential) *FlashRecognizer

NewFlashRecognizer creates instance of FlashRecognizer

func (*FlashRecognizer) Recognize added in v1.0.3 

func (recognizer *FlashRecognizer) Recognize(req *FlashRecognitionRequest,
	videoData []byte) (*FlashRecognitionResponse, error)

Recognize Recognize

type FlashWordData added in v1.0.3 

type FlashWordData struct {
	Word       string `json:"word"`
	StartTime  uint32 `json:"start_time"`
	EndTime    uint32 `json:"end_time"`
	StableFlag uint32 `json:"stable_flag"`
}

FlashWordData FlashWordData

type SpeechRecognitionListener 

type SpeechRecognitionListener interface {
	OnRecognitionStart(*SpeechRecognitionResponse)
	OnSentenceBegin(*SpeechRecognitionResponse)
	OnRecognitionResultChange(*SpeechRecognitionResponse)
	OnSentenceEnd(*SpeechRecognitionResponse)
	OnRecognitionComplete(*SpeechRecognitionResponse)
	OnFail(*SpeechRecognitionResponse, error)
}

SpeechRecognitionListener User must impletement it. Get recognition result

type SpeechRecognitionResponse 

type SpeechRecognitionResponse struct {
	Code      int                             `json:"code"`
	Message   string                          `json:"message"`
	VoiceID   string                          `json:"voice_id,omitempty"`
	MessageID string                          `json:"message_id,omitempty"`
	Final     uint32                          `json:"final,omitempty"`
	Result    SpeechRecognitionResponseResult `json:"result,omitempty"`
}

SpeechRecognitionResponse is the reponse of asr service

type SpeechRecognitionResponseResult 

type SpeechRecognitionResponseResult struct {
	SliceType    uint32                                `json:"slice_type"`
	Index        int                                   `json:"index"`
	StartTime    uint32                                `json:"start_time"`
	EndTime      uint32                                `json:"end_time"`
	VoiceTextStr string                                `json:"voice_text_str"`
	WordSize     uint32                                `json:"word_size"`
	WordList     []SpeechRecognitionResponseResultWord `json:"word_list"`
}

SpeechRecognitionResponseResult SpeechRecognitionResponseResult

type SpeechRecognitionResponseResultWord 

type SpeechRecognitionResponseResultWord struct {
	Word       string `json:"word"`
	StartTime  uint32 `json:"start_time"`
	EndTime    uint32 `json:"end_time"`
	StableFlag uint32 `json:"stable_flag"`
}

SpeechRecognitionResponseResultWord SpeechRecognitionResponseResultWord

type SpeechRecognizer 

type SpeechRecognizer struct {
	//request params
	AppID             string
	EngineModelType   string
	VoiceFormat       int
	NeedVad           int
	HotwordId         string
	HotwordList       string
	CustomizationId   string
	FilterDirty       int
	FilterModal       int
	FilterPunc        int
	ConvertNumMode    int
	WordInfo          int
	VadSilenceTime    int
	ReinforceHotword  int
	NoiseThreshold    float64
	FilterEmptyResult int
	MaxSpeakTime      int
	ReplaceTextId     string

	Credential *common.Credential

	//uuid for voice
	VoiceID string

	//for proxy
	ProxyURL string
	// contains filtered or unexported fields
}

SpeechRecognizer is the entry for ASR service

func NewSpeechRecognizer 

func NewSpeechRecognizer(appID string, credential *common.Credential, engineModelType string,
	listener SpeechRecognitionListener) *SpeechRecognizer

NewSpeechRecognizer creates instance of SpeechRecognizer

func (*SpeechRecognizer) Start 

func (recognizer *SpeechRecognizer) Start() error

Start connects to server and start a recognition session

func (*SpeechRecognizer) Stop 

func (recognizer *SpeechRecognizer) Stop() error

Stop wait for the recognition process to complete

func (*SpeechRecognizer) Write 

func (recognizer *SpeechRecognizer) Write(data []byte) error

Write : write data in channel

type VNRecognitionEvent added in v1.0.13 

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

type VNRecognitionListener added in v1.0.13 

type VNRecognitionListener interface {
	OnVNRecognitionStart(*VNRecognitionResponse)
	OnVNRecognitionComplete(*VNRecognitionResponse)
	OnVNFail(*VNRecognitionResponse, error)
}

VNRecognitionListener User must impletement it. Get recognition result

type VNRecognitionResponse added in v1.0.13 

type VNRecognitionResponse struct {
	Code      int    `json:"code"`
	Message   string `json:"message"`
	VoiceID   string `json:"voice_id,omitempty"`
	MessageID string `json:"message_id,omitempty"`
	Final     uint32 `json:"final,omitempty"`
	Result    uint32 `json:"result"`
}

VNRecognitionResponse is the reponse of asr service

type VNRecognizer added in v1.0.13 

type VNRecognizer struct {
	//request params
	AppID       string
	VoiceFormat int
	WaitTime    uint32 //等待时长 填0 后台默认30秒 最大60秒 单位毫秒

	Credential *common.Credential

	//uuid for voice
	VoiceID string

	//for proxy
	ProxyURL string
	// contains filtered or unexported fields
}

VNRecognizer is the entry for ASR service

func NewVNRecognizer added in v1.0.13 

func NewVNRecognizer(appID string, credential *common.Credential,
	listener VNRecognitionListener) *VNRecognizer

NewVNRecognizer creates instance of VNRecognizer

func (*VNRecognizer) Start added in v1.0.13 

func (recognizer *VNRecognizer) Start() error

Start connects to server and start a recognition session

func (*VNRecognizer) Stop added in v1.0.13 

func (recognizer *VNRecognizer) Stop() error

Stop wait for the recognition process to complete

func (*VNRecognizer) Write added in v1.0.13 

func (recognizer *VNRecognizer) Write(data []byte) (error, bool)

Write : write data in channel

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.