Structs§
- Candidate
Transcript - @brief A single transcript computed by the model, including a confidence value and the metadata for its constituent tokens.
- Metadata
- @brief An array of CandidateTranscript objects computed by the model.
- Model
State - Streaming
State - Token
Metadata - @brief Stores text of an individual token, along with its timing information
- max_
align_ t
Constants§
- Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ CLEAR_ HOTWORD - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ CREATE_ MODEL - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ CREATE_ SESS - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ CREATE_ STREAM - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ ERASE_ HOTWORD - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ INIT_ MMAP - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ INIT_ SESS - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ INSERT_ HOTWORD - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ INTERPRETER - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ READ_ PROTOBUF - Deep
Speech_ Error_ Codes_ DS_ ERR_ FAIL_ RUN_ SESS - Deep
Speech_ Error_ Codes_ DS_ ERR_ INVALID_ ALPHABET - Deep
Speech_ Error_ Codes_ DS_ ERR_ INVALID_ SCORER - Deep
Speech_ Error_ Codes_ DS_ ERR_ INVALID_ SHAPE - Deep
Speech_ Error_ Codes_ DS_ ERR_ MODEL_ INCOMPATIBLE - Deep
Speech_ Error_ Codes_ DS_ ERR_ NO_ MODEL - Deep
Speech_ Error_ Codes_ DS_ ERR_ OK - Deep
Speech_ Error_ Codes_ DS_ ERR_ SCORER_ INVALID_ LM - Deep
Speech_ Error_ Codes_ DS_ ERR_ SCORER_ INVALID_ TRIE - Deep
Speech_ Error_ Codes_ DS_ ERR_ SCORER_ NOT_ ENABLED - Deep
Speech_ Error_ Codes_ DS_ ERR_ SCORER_ NO_ TRIE - Deep
Speech_ Error_ Codes_ DS_ ERR_ SCORER_ UNREADABLE - Deep
Speech_ Error_ Codes_ DS_ ERR_ SCORER_ VERSION_ MISMATCH
Functions§
- DS_
AddHot ⚠Word - @brief Add a hot-word and its boost.
- DS_
Clear ⚠HotWords - @brief Removes all elements from the hot-words map.
- DS_
Create ⚠Model - @brief An object providing an interface to a trained DeepSpeech model.
- DS_
Create ⚠Stream - @brief Create a new streaming inference state. The streaming state returned by this function can then be passed to {@link DS_FeedAudioContent()} and {@link DS_FinishStream()}.
- DS_
Disable ⚠External Scorer - @brief Disable decoding using an external scorer.
- DS_
Enable ⚠External Scorer - @brief Enable decoding using an external scorer.
- DS_
Erase ⚠HotWord - @brief Remove entry for a hot-word from the hot-words map.
- DS_
Error ⚠Code ToError Message - @brief Returns a textual description corresponding to an error code. The string returned must be freed with @{link DS_FreeString()}.
- DS_
Feed ⚠Audio Content - @brief Feed audio samples to an ongoing streaming inference.
- DS_
Finish ⚠Stream - @brief Compute the final decoding of an ongoing streaming inference and return the result. Signals the end of an ongoing streaming inference.
- DS_
Finish ⚠Stream With Metadata - @brief Compute the final decoding of an ongoing streaming inference and return results including metadata. Signals the end of an ongoing streaming inference.
- DS_
Free ⚠Metadata - @brief Free memory allocated for metadata information.
- DS_
Free ⚠Model - @brief Frees associated resources and destroys model object.
- DS_
Free ⚠Stream - @brief Destroy a streaming state without decoding the computed logits. This can be used if you no longer need the result of an ongoing streaming inference and don’t want to perform a costly decode operation.
- DS_
Free ⚠String - @brief Free a char* string returned by the DeepSpeech API.
- DS_
GetModel ⚠Beam Width - @brief Get beam width value used by the model. If {@link DS_SetModelBeamWidth} was not called before, will return the default value loaded from the model file.
- DS_
GetModel ⚠Sample Rate - @brief Return the sample rate expected by a model.
- DS_
Intermediate ⚠Decode - @brief Compute the intermediate decoding of an ongoing streaming inference.
- DS_
Intermediate ⚠Decode With Metadata - @brief Compute the intermediate decoding of an ongoing streaming inference, return results including metadata.
- DS_
SetModel ⚠Beam Width - @brief Set beam width value used by the model.
- DS_
SetScorer ⚠Alpha Beta - @brief Set hyperparameters alpha and beta of the external scorer.
- DS_
Speech ⚠ToText - @brief Use the DeepSpeech model to convert speech to text.
- DS_
Speech ⚠ToText With Metadata - @brief Use the DeepSpeech model to convert speech to text and output results including metadata.
- DS_
Version ⚠ - @brief Returns the version of this library. The returned version is a semantic version (SemVer 2.0.0). The string returned must be freed with {@link DS_FreeString()}.