Documentation ¶
Index ¶
- Constants
- type FlashRecognitionRequest
- type FlashRecognitionResponse
- type FlashRecognitionResult
- type FlashRecognitionSentence
- type FlashRecognizer
- type FlashWordData
- type SpeechRecognitionListener
- type SpeechRecognitionResponse
- type SpeechRecognitionResponseResult
- type SpeechRecognitionResponseResultWord
- type SpeechRecognizer
Constants ¶
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 ¶
type FlashRecognitionRequest struct { EngineType string `json:"engine_type"` VoiceFormat string `json:"voice_format"` SpeakerDiarization uint32 `json:"speaker_diarization"` HotwordId string `json:"hotword_id"` 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 ¶
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 ¶
type FlashRecognitionResult struct { Text string `json:"text"` ChannelId int32 `json:"channel_id"` SentenceList []*FlashRecognitionSentence `json:"sentence_list,omitempty"` }
FlashRecognitionResult FlashRecognitionResult
type FlashRecognitionSentence ¶
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 ¶
type FlashRecognizer struct { AppID string //for proxy ProxyURL string Credential *common.Credential }
FlashRecognizer is the entry for ASR flash recognizer
func NewFlashRecognizer ¶
func NewFlashRecognizer(appID string, credential *common.Credential) *FlashRecognizer
NewFlashRecognizer creates instance of FlashRecognizer
func (*FlashRecognizer) Recognize ¶
func (recognizer *FlashRecognizer) Recognize(req *FlashRecognitionRequest, videoData []byte) (*FlashRecognitionResponse, error)
Recognize Recognize
type FlashWordData ¶
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 CustomizationId string FilterDirty int FilterModal int FilterPunc int ConvertNumMode int WordInfo int VadSilenceTime int ReinforceHotword int NoiseThreshold int FilterEmptyResult int 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) SetHost ¶
func (recognizer *SpeechRecognizer) SetHost(host string)
SetHost 设置请求host地址
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