Data structures


struct Metadata

Stores the entire CTC output as an array of character metadata objects.

Public Members

MetadataItem *items

List of items

int num_items

Size of the list of items

double confidence

Approximated confidence value for this transcription. This is roughly the sum of the acoustic model logit values for each timestep/character that contributed to the creation of this transcription.


struct MetadataItem

Stores each individual character, along with its timing information.

Public Members

char *character

The character generated for transcription

int timestep

Position of the character in units of 20ms

float start_time

Position of the character in seconds