Crate vosk

source · []
Expand description

Safe FFI bindings around the Vosk API Speech Recognition Toolkit.

Basic usage:


An alternative transcript in a CompleteResultMultiple.
Recognition result if Recognizer::set_max_alternatives is passed a non-zero value.
Recognition result if Recognizer::set_max_alternatives is passed a zero (default).
Model that stores all the data required for recognition.
Result returned by Recognizer::partial_result. The result may change after processing more data as decoding is not yet complete.
The main object which processes data. Takes audio as input and returns decoded information as words, confidences, times, and other metadata.
Data useful for speaker identification.
The same as Model but contains the data for speaker identification.
A single word in a CompleteResultSingle and metadata about it.
A single word in an Alternative and metadata about it.


Different results that can be returned from Recognizer::result and Recognizer::final_result.
State of the decodification after processing a chunk of data.
Log level for Kaldi messages.


Set log level for Kaldi messages.