sherpa_onnx

type AudioEvent struct {
	Name  string
	Index int
	Prob  float32
}

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

type AudioTaggingConfig struct {
	Model  AudioTaggingModelConfig
	Labels string
	TopK   int32
}

type AudioTaggingModelConfig struct {
	Zipformer  OfflineZipformerAudioTaggingModelConfig
	Ced        string
	NumThreads int32
	Debug      int32
	Provider   string
}

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

type DenoisedAudio struct {
	// Normalized samples in the range [-1, 1]
	Samples []float32

	SampleRate int
}

type FastClusteringConfig struct {
	NumClusters int
	Threshold   float32
}

type FeatureConfig struct {
	// Sample rate expected by the model. It is 16000 for all
	// pre-trained models provided by us
	SampleRate int
	// Feature dimension expected by the model. It is 80 for all
	// pre-trained models provided by us
	FeatureDim int
}

type GeneratedAudio struct {
	// Normalized samples in the range [-1, 1]
	Samples []float32

	SampleRate int
}

type HomophoneReplacerConfig struct {
	DictDir  string // unused
	Lexicon  string
	RuleFsts string
}

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

type KeywordSpotterConfig struct {
	FeatConfig        FeatureConfig
	ModelConfig       OnlineModelConfig
	MaxActivePaths    int
	KeywordsFile      string
	KeywordsScore     float32
	KeywordsThreshold float32
	KeywordsBuf       string
	KeywordsBufSize   int
}

type KeywordSpotterResult struct {
	Keyword string
}

type OfflineCanaryModelConfig struct {
	Encoder string
	Decoder string
	SrcLang string
	TgtLang string
	UsePnc  int
}

type OfflineDolphinModelConfig struct {
	Model string // Path to the model, e.g., model.onnx or model.int8.onnx
}

type OfflineFireRedAsrModelConfig struct {
	Encoder string
	Decoder string
}

type OfflineLMConfig struct {
	Model string  // Path to the model
	Scale float32 // scale for LM score
}

type OfflineModelConfig struct {
	Transducer   OfflineTransducerModelConfig
	Paraformer   OfflineParaformerModelConfig
	NemoCTC      OfflineNemoEncDecCtcModelConfig
	Whisper      OfflineWhisperModelConfig
	Tdnn         OfflineTdnnModelConfig
	SenseVoice   OfflineSenseVoiceModelConfig
	Moonshine    OfflineMoonshineModelConfig
	FireRedAsr   OfflineFireRedAsrModelConfig
	Dolphin      OfflineDolphinModelConfig
	ZipformerCtc OfflineZipformerCtcModelConfig
	Canary       OfflineCanaryModelConfig
	WenetCtc     OfflineWenetCtcModelConfig
	Omnilingual  OfflineOmnilingualAsrCtcModelConfig
	Tokens       string // Path to tokens.txt

	// Number of threads to use for neural network computation
	NumThreads int

	// 1 to print model meta information while loading
	Debug int

	// Optional. Valid values: cpu, cuda, coreml
	Provider string

	// Optional. Specify it for faster model initialization.
	ModelType string

	ModelingUnit  string // Optional. cjkchar, bpe, cjkchar+bpe
	BpeVocab      string // Optional.
	TeleSpeechCtc string // Optional.
}

type OfflineMoonshineModelConfig struct {
	Preprocessor    string
	Encoder         string
	UncachedDecoder string
	CachedDecoder   string
}

type OfflineNemoEncDecCtcModelConfig struct {
	Model string // Path to the model, e.g., model.onnx or model.int8.onnx
}

type OfflineOmnilingualAsrCtcModelConfig struct {
	Model string // Path to the model, e.g., model.onnx or model.int8.onnx
}

type OfflineParaformerModelConfig struct {
	Model string // Path to the model, e.g., model.onnx or model.int8.onnx
}

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

type OfflinePunctuationConfig struct {
	Model OfflinePunctuationModelConfig
}

type OfflinePunctuationModelConfig struct {
	CtTransformer string
	NumThreads    C.int
	Debug         C.int // true to print debug information of the model
	Provider      string
}

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

type OfflineRecognizerConfig struct {
	FeatConfig  FeatureConfig
	ModelConfig OfflineModelConfig
	LmConfig    OfflineLMConfig

	// Valid decoding method: greedy_search, modified_beam_search
	DecodingMethod string

	// Used only when DecodingMethod is modified_beam_search.
	MaxActivePaths int
	HotwordsFile   string
	HotwordsScore  float32
	BlankPenalty   float32
	RuleFsts       string
	RuleFars       string
	Hr             HomophoneReplacerConfig
}

type OfflineRecognizerResult struct {
	Text       string
	Tokens     []string
	Timestamps []float32
	Durations  []float32
	Lang       string
	Emotion    string
	Event      string
}

type OfflineSenseVoiceModelConfig struct {
	Model                       string
	Language                    string
	UseInverseTextNormalization int
}

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

type OfflineSpeakerDiarizationConfig struct {
	Segmentation   OfflineSpeakerSegmentationModelConfig
	Embedding      SpeakerEmbeddingExtractorConfig
	Clustering     FastClusteringConfig
	MinDurationOn  float32
	MinDurationOff float32
}

type OfflineSpeakerDiarizationSegment struct {
	Start   float32
	End     float32
	Speaker int
}

type OfflineSpeakerSegmentationModelConfig struct {
	Pyannote   OfflineSpeakerSegmentationPyannoteModelConfig
	NumThreads int
	Debug      int
	Provider   string
}

type OfflineSpeakerSegmentationPyannoteModelConfig struct {
	Model string
}

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

type OfflineSpeechDenoiserConfig struct {
	Model OfflineSpeechDenoiserModelConfig
}

type OfflineSpeechDenoiserGtcrnModelConfig struct {
	Model string
}

type OfflineSpeechDenoiserModelConfig struct {
	Gtcrn      OfflineSpeechDenoiserGtcrnModelConfig
	NumThreads int32
	Debug      int32
	Provider   string
}

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

type OfflineTdnnModelConfig struct {
	Model string
}

type OfflineTransducerModelConfig struct {
	Encoder string // Path to the encoder model, i.e., encoder.onnx or encoder.int8.onnx
	Decoder string // Path to the decoder model
	Joiner  string // Path to the joiner model
}

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

type OfflineTtsConfig struct {
	Model           OfflineTtsModelConfig
	RuleFsts        string
	RuleFars        string
	MaxNumSentences int
	SilenceScale    float32
}

type OfflineTtsKittenModelConfig struct {
	Model       string  // Path to the model for kitten
	Voices      string  // Path to the voices.bin for kitten
	Tokens      string  // Path to tokens.txt
	DataDir     string  // Path to espeak-ng-data directory
	LengthScale float32 // Please use 1.0 in general. Smaller -> Faster speech speed. Larger -> Slower speech speed
}

type OfflineTtsKokoroModelConfig struct {
	Model       string  // Path to the model for kokoro
	Voices      string  // Path to the voices.bin for kokoro
	Tokens      string  // Path to tokens.txt
	DataDir     string  // Path to espeak-ng-data directory
	DictDir     string  // unused
	Lexicon     string  // Path to lexicon files
	Lang        string  // Example: es for Spanish, fr-fr for French. Can be empty
	LengthScale float32 // Please use 1.0 in general. Smaller -> Faster speech speed. Larger -> Slower speech speed
}

type OfflineTtsMatchaModelConfig struct {
	AcousticModel string  // Path to the acoustic model for MatchaTTS
	Vocoder       string  // Path to the vocoder model for MatchaTTS
	Lexicon       string  // Path to lexicon.txt
	Tokens        string  // Path to tokens.txt
	DataDir       string  // Path to espeak-ng-data directory
	NoiseScale    float32 // noise scale for vits models. Please use 0.667 in general
	LengthScale   float32 // Please use 1.0 in general. Smaller -> Faster speech speed. Larger -> Slower speech speed
	DictDir       string  // unused
}

type OfflineTtsModelConfig struct {
	Vits     OfflineTtsVitsModelConfig
	Matcha   OfflineTtsMatchaModelConfig
	Kokoro   OfflineTtsKokoroModelConfig
	Kitten   OfflineTtsKittenModelConfig
	Zipvoice OfflineTtsZipvoiceModelConfig

	// Number of threads to use for neural network computation
	NumThreads int

	// 1 to print model meta information while loading
	Debug int

	// Optional. Valid values: cpu, cuda, coreml
	Provider string
}

type OfflineTtsVitsModelConfig struct {
	Model       string  // Path to the VITS onnx model
	Lexicon     string  // Path to lexicon.txt
	Tokens      string  // Path to tokens.txt
	DataDir     string  // Path to espeak-ng-data directory
	NoiseScale  float32 // noise scale for vits models. Please use 0.667 in general
	NoiseScaleW float32 // noise scale for vits models. Please use 0.8 in general
	LengthScale float32 // Please use 1.0 in general. Smaller -> Faster speech speed. Larger -> Slower speech speed
	DictDir     string  // unused
}

type OfflineTtsZipvoiceModelConfig struct {
	Tokens  string // Path to tokens.txt for ZipVoice
	Encoder string // Path to text encoder (e.g. encoder.onnx)
	Decoder string // Path to flow-matching decoder (e.g. fm_decoder.onnx)
	DataDir string // Path to espeak-ng-data
	Lexicon string // Path to lexicon.txt (needed for zh)
	Vocoder string // Path to vocoder (e.g. vocos_24khz.onnx)

	FeatScale     float32 // Feature scale
	TShift        float32 // t-shift (<1 shifts to smaller t)
	TargetRms     float32 // Target RMS for speech normalization
	GuidanceScale float32 // CFG scale
}

type OfflineWenetCtcModelConfig struct {
	Model string // Path to the model, e.g., model.onnx or model.int8.onnx
}

type OfflineWhisperModelConfig struct {
	Encoder      string
	Decoder      string
	Language     string
	Task         string
	TailPaddings int
}

type OfflineZipformerAudioTaggingModelConfig struct {
	Model string
}

type OfflineZipformerCtcModelConfig struct {
	Model string // Path to the model, e.g., model.onnx or model.int8.onnx
}

type OnlineCtcFstDecoderConfig struct {
	Graph     string
	MaxActive int
}

type OnlineModelConfig struct {
	Transducer    OnlineTransducerModelConfig
	Paraformer    OnlineParaformerModelConfig
	Zipformer2Ctc OnlineZipformer2CtcModelConfig
	NemoCtc       OnlineNemoCtcModelConfig
	ToneCtc       OnlineToneCtcModelConfig
	Tokens        string // Path to tokens.txt
	NumThreads    int    // Number of threads to use for neural network computation
	Provider      string // Optional. Valid values are: cpu, cuda, coreml
	Debug         int    // 1 to show model meta information while loading it.
	ModelType     string // Optional. You can specify it for faster model initialization
	ModelingUnit  string // Optional. cjkchar, bpe, cjkchar+bpe
	BpeVocab      string // Optional.
	TokensBuf     string // Optional.
	TokensBufSize int    // Optional.
}

type OnlineNemoCtcModelConfig struct {
	Model string // Path to the onnx model
}

type OnlineParaformerModelConfig struct {
	Encoder string // Path to the encoder model, e.g., encoder.onnx or encoder.int8.onnx
	Decoder string // Path to the decoder model.
}

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

type OnlineRecognizerConfig struct {
	FeatConfig  FeatureConfig
	ModelConfig OnlineModelConfig

	// Valid decoding methods: greedy_search, modified_beam_search
	DecodingMethod string

	// Used only when DecodingMethod is modified_beam_search. It specifies
	// the maximum number of paths to keep during the search
	MaxActivePaths int

	EnableEndpoint int // 1 to enable endpoint detection.

	// Please see
	// https://k2-fsa.github.io/sherpa/ncnn/endpoint.html
	// for the meaning of Rule1MinTrailingSilence, Rule2MinTrailingSilence
	// and Rule3MinUtteranceLength.
	Rule1MinTrailingSilence float32
	Rule2MinTrailingSilence float32
	Rule3MinUtteranceLength float32
	HotwordsFile            string
	HotwordsScore           float32
	BlankPenalty            float32
	CtcFstDecoderConfig     OnlineCtcFstDecoderConfig
	RuleFsts                string
	RuleFars                string
	HotwordsBuf             string
	HotwordsBufSize         int
	Hr                      HomophoneReplacerConfig
}

type OnlineRecognizerResult struct {
	Text string
}

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

type OnlineToneCtcModelConfig struct {
	Model string // Path to the onnx model
}

type OnlineTransducerModelConfig struct {
	Encoder string // Path to the encoder model, e.g., encoder.onnx or encoder.int8.onnx
	Decoder string // Path to the decoder model.
	Joiner  string // Path to the joiner model.
}

type OnlineZipformer2CtcModelConfig struct {
	Model string // Path to the onnx model
}

type SileroVadModelConfig struct {
	Model              string
	Threshold          float32
	MinSilenceDuration float32
	MinSpeechDuration  float32
	WindowSize         int
	MaxSpeechDuration  float32
}

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

type SpeakerEmbeddingExtractorConfig struct {
	Model      string
	NumThreads int
	Debug      int
	Provider   string
}

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

type SpeechSegment struct {
	Start   int
	Samples []float32
}

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

type SpokenLanguageIdentificationConfig struct {
	Whisper    SpokenLanguageIdentificationWhisperConfig
	NumThreads int
	Debug      int
	Provider   string
}

type SpokenLanguageIdentificationResult struct {
	Lang string
}

type SpokenLanguageIdentificationWhisperConfig struct {
	Encoder      string
	Decoder      string
	TailPaddings int
}

type TenVadModelConfig struct {
	Model              string
	Threshold          float32
	MinSilenceDuration float32
	MinSpeechDuration  float32
	WindowSize         int
	MaxSpeechDuration  float32
}

type VadModelConfig struct {
	SileroVad  SileroVadModelConfig
	TenVad     TenVadModelConfig
	SampleRate int
	NumThreads int
	Provider   string
	Debug      int
}

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

type Wave = GeneratedAudio