Releases batch model object
Creates the batch recognizer object
Wait for the processing
Accept batch voice data
Closes the stream
Releases batch recognizer object
Return results
Get amount of pending chunks for more intelligent waiting
Creates batch recognizer object
@returns recognizer object or NULL if problem occured
Release and free first retrieved result
Set NLSML output
@param nlsml - boolean value
Init, automatically select a CUDA device and allow multithreading.
Must be called once from the main thread.
Has no effect if HAVE_CUDA flag is not set.
Init CUDA device in a multi-threaded environment.
Must be called for each thread.
Has no effect if HAVE_CUDA flag is not set.
Check if a word can be recognized by the model
@param word: the word
@returns the word symbol if @param word exists inside the model
or -1 otherwise.
Reminding that word symbol 0 is for <epsilon>
Releases the model memory
Loads model data from the file and returns the model object
Accept voice data
Same as above but the version with the float data for language bindings where you have
audio as array of floats
Same as above but the version with the short data for language bindings where you have
audio as array of shorts
Returns speech recognition result. Same as result, but doesn’t wait for silence
You usually call it in the end of the stream to get final bits of audio. It
flushes the feature pipeline, so all remaining audio chunks got processed.
Releases recognizer object
Creates the recognizer object
Creates the recognizer object with the phrase list
Creates the recognizer object with speaker recognition
Returns partial speech recognition
Resets the recognizer
Returns speech recognition result
Configures recognizer to output n-best results
Set NLSML output
@param nlsml - boolean value
Like above return words and confidences in partial results
Adds speaker model to already initialized recognizer
Enables words with times in the output
Set log level for Kaldi messages
Releases the model memory
Loads speaker model data from the file and returns the model object