sherpa-onnx C API 1.0
Public C API and C++ wrapper for sherpa-onnx
Loading...
Searching...
No Matches
Class Hierarchy

Go to the graphical class hierarchy

This inheritance list is sorted roughly, but not completely, alphabetically:
[detail level 12]
 Csherpa_onnx::cxx::AudioEventOne audio-tagging event returned by the C++ wrapper
 Csherpa_onnx::cxx::AudioTaggingConfigConfiguration for audio tagging
 Csherpa_onnx::cxx::AudioTaggingModelConfigAudio-tagging model configuration
 Csherpa_onnx::cxx::DenoisedAudioDenoised waveform returned by speech enhancement wrappers
 Csherpa_onnx::cxx::FastClusteringConfigFast clustering configuration
 Csherpa_onnx::cxx::FeatureConfigFeature extraction settings shared by ASR and KWS wrappers
 Csherpa_onnx::cxx::ForcedAlignerConfigConfiguration of a forced aligner
 Csherpa_onnx::cxx::ForcedAlignmentIntervalOne aligned interval: a phone in the "phones" tier or a word in the "words" tier
 Csherpa_onnx::cxx::ForcedAlignmentOptionsOptions of a forced aligner
 Csherpa_onnx::cxx::ForcedAlignmentResultThe result of ForcedAligner::Compute()
 Csherpa_onnx::cxx::ForcedAlignmentTierOne tier of the alignment (phones or words)
 Csherpa_onnx::cxx::GeneratedAudioGenerated audio returned by the C++ TTS wrapper
 Csherpa_onnx::cxx::GenerationConfigGeneration-time options for advanced TTS synthesis
 Csherpa_onnx::cxx::HomophoneReplacerConfigHomophone replacement resources used by some Chinese ASR setups
 Csherpa_onnx::cxx::KeywordResultCurrent keyword spotting result copied into C++ containers
 Csherpa_onnx::cxx::KeywordSpotterConfigConfiguration for the C++ keyword spotting wrapper
 Csherpa_onnx::cxx::MoveOnly< Derived, T >Base class for move-only RAII wrappers around C handles
 Csherpa_onnx::cxx::MoveOnly< AudioTagging, SherpaOnnxAudioTagging >
 Csherpa_onnx::cxx::MoveOnly< CircularBuffer, SherpaOnnxCircularBuffer >
 Csherpa_onnx::cxx::MoveOnly< ForcedAligner, SherpaOnnxForcedAligner >
 Csherpa_onnx::cxx::MoveOnly< KeywordSpotter, SherpaOnnxKeywordSpotter >
 Csherpa_onnx::cxx::MoveOnly< LinearResampler, SherpaOnnxLinearResampler >
 Csherpa_onnx::cxx::MoveOnly< OfflineDiacritization, SherpaOnnxOfflineDiacritization >
 Csherpa_onnx::cxx::MoveOnly< OfflinePunctuation, SherpaOnnxOfflinePunctuation >
 Csherpa_onnx::cxx::MoveOnly< OfflineRecognizer, SherpaOnnxOfflineRecognizer >
 Csherpa_onnx::cxx::MoveOnly< OfflineSourceSeparation, SherpaOnnxOfflineSourceSeparation >
 Csherpa_onnx::cxx::MoveOnly< OfflineSpeakerDiarization, SherpaOnnxOfflineSpeakerDiarization >
 Csherpa_onnx::cxx::MoveOnly< OfflineSpeechDenoiser, SherpaOnnxOfflineSpeechDenoiser >
 Csherpa_onnx::cxx::MoveOnly< OfflineStream, SherpaOnnxOfflineStream >
 Csherpa_onnx::cxx::MoveOnly< OfflineTts, SherpaOnnxOfflineTts >
 Csherpa_onnx::cxx::MoveOnly< OnlinePunctuation, SherpaOnnxOnlinePunctuation >
 Csherpa_onnx::cxx::MoveOnly< OnlineRecognizer, SherpaOnnxOnlineRecognizer >
 Csherpa_onnx::cxx::MoveOnly< OnlineSpeechDenoiser, SherpaOnnxOnlineSpeechDenoiser >
 Csherpa_onnx::cxx::MoveOnly< OnlineStream, SherpaOnnxOnlineStream >
 Csherpa_onnx::cxx::MoveOnly< SpeakerEmbeddingExtractor, SherpaOnnxSpeakerEmbeddingExtractor >
 Csherpa_onnx::cxx::MoveOnly< SpeakerEmbeddingManager, SherpaOnnxSpeakerEmbeddingManager >
 Csherpa_onnx::cxx::MoveOnly< SpokenLanguageIdentification, SherpaOnnxSpokenLanguageIdentification >
 Csherpa_onnx::cxx::MoveOnly< VoiceActivityDetector, SherpaOnnxVoiceActivityDetector >
 Csherpa_onnx::cxx::OfflineCanaryModelConfigOffline Canary model configuration
 Csherpa_onnx::cxx::OfflineCohereTranscribeModelConfigOffline Cohere Transcribe model configuration
 Csherpa_onnx::cxx::OfflineCtcFstDecoderConfigDecoder graph configuration for offline CTC + FST decoding
 Csherpa_onnx::cxx::OfflineDiacritizationConfigConfiguration for offline diacritization
 Csherpa_onnx::cxx::OfflineDiacritizationModelConfigOffline diacritization model configuration
 Csherpa_onnx::cxx::OfflineDolphinModelConfigOffline Dolphin model file
 Csherpa_onnx::cxx::OfflineFireRedAsrCtcModelConfigOffline FireRed ASR CTC model file
 Csherpa_onnx::cxx::OfflineFireRedAsrModelConfigOffline FireRed ASR model files
 Csherpa_onnx::cxx::OfflineFunASRNanoModelConfigOffline FunASR Nano model configuration
 Csherpa_onnx::cxx::OfflineLMConfigOptional language-model rescoring configuration for offline ASR
 Csherpa_onnx::cxx::OfflineMedAsrCtcModelConfigOffline MedASR CTC model file
 Csherpa_onnx::cxx::OfflineModelConfigAcoustic model configuration for offline ASR
 Csherpa_onnx::cxx::OfflineMoonshineModelConfigOffline Moonshine model configuration
 Csherpa_onnx::cxx::OfflineNemoEncDecCtcModelConfigOffline NeMo EncDec CTC model file
 Csherpa_onnx::cxx::OfflineOmnilingualAsrCtcModelConfigOffline omnilingual ASR CTC model file
 Csherpa_onnx::cxx::OfflineParaformerModelConfigOffline Paraformer model file
 Csherpa_onnx::cxx::OfflinePunctuationConfigConfiguration for offline punctuation
 Csherpa_onnx::cxx::OfflinePunctuationModelConfigOffline punctuation model configuration
 Csherpa_onnx::cxx::OfflineQwen3ASRModelConfigOffline Qwen3-ASR model configuration
 Csherpa_onnx::cxx::OfflineRecognizerConfigConfiguration for offline ASR
 Csherpa_onnx::cxx::OfflineRecognizerResultOffline ASR result copied into C++ containers
 Csherpa_onnx::cxx::OfflineSenseVoiceModelConfigOffline SenseVoice model configuration
 Csherpa_onnx::cxx::OfflineSourceSeparationConfigConfiguration for offline source separation
 Csherpa_onnx::cxx::OfflineSourceSeparationModelConfigSource-separation model configuration
 Csherpa_onnx::cxx::OfflineSourceSeparationSpleeterModelConfigSpleeter source-separation model configuration
 Csherpa_onnx::cxx::OfflineSourceSeparationUvrModelConfigUVR (MDX-Net) source-separation model configuration
 Csherpa_onnx::cxx::OfflineSpeakerDiarizationConfigConfiguration for offline speaker diarization
 Csherpa_onnx::cxx::OfflineSpeakerDiarizationSegmentOne diarization segment
 Csherpa_onnx::cxx::OfflineSpeakerSegmentationModelConfigSegmentation model configuration for offline speaker diarization
 Csherpa_onnx::cxx::OfflineSpeakerSegmentationPyannoteModelConfigPyannote segmentation model configuration
 Csherpa_onnx::cxx::OfflineSpeechDenoiserConfigConfiguration for offline speech denoising
 Csherpa_onnx::cxx::OfflineSpeechDenoiserDpdfNetModelConfigDPDFNet speech denoiser model configuration
 Csherpa_onnx::cxx::OfflineSpeechDenoiserGtcrnModelConfigGTCRN speech denoiser model configuration
 Csherpa_onnx::cxx::OfflineSpeechDenoiserModelConfigSpeech denoiser model configuration
 Csherpa_onnx::cxx::OfflineSpeechDenoiserVoxLockModelConfigVoxLock target-speaker voice isolation model configuration
 Csherpa_onnx::cxx::OfflineTdnnModelConfigOffline TDNN model file
 Csherpa_onnx::cxx::OfflineTransducerModelConfigOffline transducer model files
 Csherpa_onnx::cxx::OfflineTtsConfigConfiguration for offline TTS
 Csherpa_onnx::cxx::OfflineTtsKittenModelConfigKitten model configuration
 Csherpa_onnx::cxx::OfflineTtsKokoroModelConfigKokoro model configuration
 Csherpa_onnx::cxx::OfflineTtsMatchaModelConfigMatcha model configuration
 Csherpa_onnx::cxx::OfflineTtsModelConfigModel configuration for offline TTS
 Csherpa_onnx::cxx::OfflineTtsPocketModelConfigPocket TTS model configuration
 Csherpa_onnx::cxx::OfflineTtsSupertonicModelConfigSupertonic model configuration
 Csherpa_onnx::cxx::OfflineTtsVitsModelConfigVITS model configuration
 Csherpa_onnx::cxx::OfflineTtsZipvoiceModelConfigZipVoice model configuration
 Csherpa_onnx::cxx::OfflineWenetCtcModelConfigOffline WeNet CTC model file
 Csherpa_onnx::cxx::OfflineWhisperModelConfigOffline Whisper model configuration
 Csherpa_onnx::cxx::OfflineZipformerAudioTaggingModelConfigZipformer audio-tagging model configuration
 Csherpa_onnx::cxx::OfflineZipformerCtcModelConfigOffline Zipformer CTC model file
 Csherpa_onnx::cxx::OnlineCtcFstDecoderConfigDecoder graph configuration for online CTC + FST decoding
 Csherpa_onnx::cxx::OnlineModelConfigAcoustic model configuration for streaming ASR
 Csherpa_onnx::cxx::OnlineNemoCtcModelConfigStreaming NeMo CTC model file
 Csherpa_onnx::cxx::OnlineParaformerModelConfigStreaming Paraformer model files
 Csherpa_onnx::cxx::OnlinePunctuationConfigConfiguration for online punctuation
 Csherpa_onnx::cxx::OnlinePunctuationModelConfigOnline punctuation model configuration
 Csherpa_onnx::cxx::OnlineRecognizerConfigConfiguration for streaming ASR
 Csherpa_onnx::cxx::OnlineRecognizerResultCurrent streaming ASR result copied into C++ containers
 Csherpa_onnx::cxx::OnlineSpeechDenoiserConfigConfiguration for online speech denoising
 Csherpa_onnx::cxx::OnlineToneCtcModelConfigStreaming T-One CTC model file
 Csherpa_onnx::cxx::OnlineTransducerModelConfigStreaming transducer model files
 Csherpa_onnx::cxx::OnlineZipformer2CtcModelConfigStreaming Zipformer2 CTC model file
 CSherpaOnnxAudioEventOne audio-tagging prediction
 CSherpaOnnxAudioTaggingConfigConfiguration for audio tagging
 CSherpaOnnxAudioTaggingModelConfigAudio-tagging model configuration
 CSherpaOnnxDenoisedAudioDenoised audio returned by offline or online speech enhancement APIs
 CSherpaOnnxFastClusteringConfigFast clustering configuration
 CSherpaOnnxFeatureConfigFeature extraction settings for ASR
 CSherpaOnnxForcedAlignerConfigConfiguration of a forced aligner
 CSherpaOnnxForcedAlignmentInterval
 CSherpaOnnxForcedAlignmentOptionsOptions of a forced aligner. A stream can override any of them via its own option mechanism before the alignment is computed
 CSherpaOnnxForcedAlignmentResultThe result of SherpaOnnxForcedAlignerCompute()
 CSherpaOnnxForcedAlignmentTier
 CSherpaOnnxGeneratedAudioGenerated waveform returned by TTS APIs
 CSherpaOnnxGenerationConfigGeneration-time parameters shared by advanced TTS APIs
 CSherpaOnnxHomophoneReplacerConfigConfiguration for homophone replacement
 CSherpaOnnxKeywordResultSnapshot of the current keyword spotting result
 CSherpaOnnxKeywordSpotterConfigConfiguration for keyword spotting
 CSherpaOnnxMultiChannelWaveDecoded multi-channel WAVE file content
 CSherpaOnnxOfflineCanaryModelConfigConfiguration for a Canary model
 CSherpaOnnxOfflineCohereTranscribeModelConfigConfiguration for a Cohere Transcribe model
 CSherpaOnnxOfflineCtcFstDecoderConfigConfiguration for HLG/FST-based offline CTC decoding
 CSherpaOnnxOfflineDiacritizationConfigConfiguration for offline diacritization
 CSherpaOnnxOfflineDiacritizationModelConfigOffline diacritization model configuration
 CSherpaOnnxOfflineDolphinModelConfigConfiguration for a Dolphin model
 CSherpaOnnxOfflineFireRedAsrCtcModelConfigConfiguration for a FireRedAsr CTC model
 CSherpaOnnxOfflineFireRedAsrModelConfigConfiguration for a FireRedAsr encoder/decoder model
 CSherpaOnnxOfflineFunASRNanoModelConfigConfiguration for an offline FunASR Nano model
 CSherpaOnnxOfflineLMConfigConfiguration for an offline language model
 CSherpaOnnxOfflineMedAsrCtcModelConfigConfiguration for a MedASR CTC model
 CSherpaOnnxOfflineModelConfigModel configuration shared by offline ASR recognizers
 CSherpaOnnxOfflineMoonshineModelConfigConfiguration for a Moonshine model
 CSherpaOnnxOfflineNemoEncDecCtcModelConfigConfiguration for a non-streaming NeMo CTC model
 CSherpaOnnxOfflineOmnilingualAsrCtcModelConfigConfiguration for an omnilingual offline CTC model
 CSherpaOnnxOfflineParaformerModelConfigConfiguration for a non-streaming Paraformer model
 CSherpaOnnxOfflinePunctuationConfigConfiguration for offline punctuation
 CSherpaOnnxOfflinePunctuationModelConfigOffline punctuation model configuration
 CSherpaOnnxOfflineQwen3ASRModelConfigConfiguration for an offline Qwen3-ASR model
 CSherpaOnnxOfflineRecognizerConfigConfiguration for a non-streaming ASR recognizer
 CSherpaOnnxOfflineRecognizerResultRecognition result for a non-streaming ASR stream
 CSherpaOnnxOfflineSenseVoiceModelConfigConfiguration for a SenseVoice model
 CSherpaOnnxOfflineSourceSeparationConfigTop-level source-separation configuration
 CSherpaOnnxOfflineSourceSeparationModelConfigSource-separation model configuration
 CSherpaOnnxOfflineSourceSeparationSpleeterModelConfigSpleeter source-separation model configuration
 CSherpaOnnxOfflineSourceSeparationUvrModelConfigUVR (MDX-Net) source-separation model configuration
 CSherpaOnnxOfflineSpeakerDiarizationConfigConfiguration for offline speaker diarization
 CSherpaOnnxOfflineSpeakerDiarizationSegmentOne diarization segment
 CSherpaOnnxOfflineSpeakerSegmentationModelConfigSegmentation model configuration for offline speaker diarization
 CSherpaOnnxOfflineSpeakerSegmentationPyannoteModelConfigPyannote speaker-segmentation model configuration
 CSherpaOnnxOfflineSpeechDenoiserConfigConfiguration for offline speech denoising
 CSherpaOnnxOfflineSpeechDenoiserDpdfNetModelConfigDPDFNet offline denoiser model configuration
 CSherpaOnnxOfflineSpeechDenoiserGtcrnModelConfigGTCRN offline denoiser model configuration
 CSherpaOnnxOfflineSpeechDenoiserModelConfigSpeech denoiser model configuration shared by offline and online APIs
 CSherpaOnnxOfflineSpeechDenoiserVoxLockModelConfigVoxLock target-speaker voice isolation model configuration
 CSherpaOnnxOfflineTdnnModelConfigConfiguration for a TDNN model
 CSherpaOnnxOfflineTransducerModelConfigConfiguration for a non-streaming transducer model
 CSherpaOnnxOfflineTtsConfigConfiguration for offline text-to-speech
 CSherpaOnnxOfflineTtsKittenModelConfigConfiguration for a Kitten TTS model
 CSherpaOnnxOfflineTtsKokoroModelConfigConfiguration for a Kokoro TTS model
 CSherpaOnnxOfflineTtsMatchaModelConfigConfiguration for a Matcha TTS model
 CSherpaOnnxOfflineTtsModelConfigConfiguration shared by offline TTS models
 CSherpaOnnxOfflineTtsPocketModelConfigConfiguration for a Pocket TTS model
 CSherpaOnnxOfflineTtsSupertonicModelConfigConfiguration for a Supertonic TTS model
 CSherpaOnnxOfflineTtsVitsModelConfigConfiguration for a VITS TTS model
 CSherpaOnnxOfflineTtsZipvoiceModelConfigConfiguration for a ZipVoice TTS model
 CSherpaOnnxOfflineWenetCtcModelConfigConfiguration for an offline WeNet CTC model
 CSherpaOnnxOfflineWhisperModelConfigConfiguration for a non-streaming Whisper model
 CSherpaOnnxOfflineZipformerAudioTaggingModelConfigZipformer audio-tagging model configuration
 CSherpaOnnxOfflineZipformerCtcModelConfigConfiguration for an offline Zipformer CTC model
 CSherpaOnnxOnlineCtcFstDecoderConfigConfiguration for HLG/FST-based online CTC decoding
 CSherpaOnnxOnlineModelConfigModel configuration shared by streaming ASR recognizers
 CSherpaOnnxOnlineNemoCtcModelConfigConfiguration for a streaming NeMo CTC model
 CSherpaOnnxOnlineParaformerModelConfigConfiguration for a streaming Paraformer model
 CSherpaOnnxOnlinePunctuationConfigConfiguration for online punctuation
 CSherpaOnnxOnlinePunctuationModelConfigOnline punctuation model configuration
 CSherpaOnnxOnlineRecognizerConfigConfiguration for a streaming ASR recognizer
 CSherpaOnnxOnlineRecognizerResultIncremental recognition result for a streaming ASR stream
 CSherpaOnnxOnlineSpeechDenoiserConfigConfiguration for streaming speech denoising
 CSherpaOnnxOnlineToneCtcModelConfigConfiguration for a streaming T-One CTC model
 CSherpaOnnxOnlineTransducerModelConfigConfiguration for a streaming transducer model
 CSherpaOnnxOnlineZipformer2CtcModelConfigConfiguration for a streaming Zipformer2 CTC model
 CSherpaOnnxResampleOutOutput chunk returned by SherpaOnnxLinearResamplerResample()
 CSherpaOnnxSileroVadModelConfigConfiguration for a Silero VAD model
 CSherpaOnnxSourceSeparationOutputOutput of a source-separation run
 CSherpaOnnxSourceSeparationStemA single stem (one output track) with one or more channels
 CSherpaOnnxSpeakerEmbeddingExtractorConfigConfiguration for speaker embedding extraction
 CSherpaOnnxSpeakerEmbeddingManagerBestMatchesResultCollection of best speaker matches
 CSherpaOnnxSpeakerEmbeddingManagerSpeakerMatchOne speaker match returned by the best-matches API
 CSherpaOnnxSpeechSegmentOne detected speech segment returned by the VAD
 CSherpaOnnxSpokenLanguageIdentificationConfigConfiguration for spoken language identification
 CSherpaOnnxSpokenLanguageIdentificationResultResult of spoken-language identification
 CSherpaOnnxSpokenLanguageIdentificationWhisperConfigWhisper-based model files for spoken language identification
 CSherpaOnnxTenVadModelConfigConfiguration for a Ten VAD model
 CSherpaOnnxVadModelConfigConfiguration shared by voice activity detectors
 CSherpaOnnxWaveDecoded mono WAVE file content
 Csherpa_onnx::cxx::SileroVadModelConfigSilero VAD model configuration
 Csherpa_onnx::cxx::SourceSeparationOutputOutput of a source-separation run
 Csherpa_onnx::cxx::SourceSeparationStemA single stem (output track) with one or more channels
 Csherpa_onnx::cxx::SpeakerEmbeddingExtractorConfigConfiguration for speaker embedding extraction
 Csherpa_onnx::cxx::SpeakerMatchOne speaker match returned by the best-matches API
 Csherpa_onnx::cxx::SpeechSegmentOne speech segment produced by the VAD wrapper
 Csherpa_onnx::cxx::SpokenLanguageIdentificationConfigConfiguration for spoken language identification
 Csherpa_onnx::cxx::SpokenLanguageIdentificationResultResult of spoken language identification
 Csherpa_onnx::cxx::SpokenLanguageIdentificationWhisperConfigWhisper model configuration for spoken language identification
 Csherpa_onnx::cxx::TenVadModelConfigTen VAD model configuration
 Csherpa_onnx::cxx::VadModelConfigVAD model configuration
 Csherpa_onnx::cxx::WaveMono PCM waveform used by the helper I/O functions