NAME
Speech::Recognition::Vosk::Recognizer - offline speech recognition using Vosk
SYNOPSIS
use Speech::Recognition::Vosk::Recognizer;
my $recognizer = Speech::Recognition::Vosk::Recognizer->new(
model_dir => 'model-en',
sample_rate => 44100,
);
# record from PulseAudio device 11
open my $voice, 'ffmpeg -hide_banner -loglevel error -nostats -f pulse -i 11 -t 30 -ac 1 -ar 44100 -f s16le - |';
binmode $voice, ':raw';
while( ! eof($voice)) {
read(STDIN, my $buf, 3200);
my $complete = $recognizer->accept_waveform($buf);
my $spoken;
if( $complete ) {
$spoken = $recognizer->result();
} else {
$spoken = $recognizer->partial_result();
}
if( $info->{text}) {
print $info->{text},"\n";
} else {
local $| = 1;
print $info->{partial}, "\r";
};
};
my $spoken = $recognizer->final_result();
print $info->{text},"\n";METHODS
->new
->accept_waveform
read($voice, my $buf, 3200);
my $complete = $recognizer->accept_waveform($buf);Feed more data to the recognizer. Returns if a pause in the speech was detected and a completed utterance is available.
->result
my $spoken = $recognizer->result();
print $spoken->{text};Returns a hashref containing the recognized text.
->partial_result
my $spoken = $recognizer->partial_result();
print "$spoken->{partial}\r";Returns a hashref containing the recognized text so far. The text may change when more data is collected.
->final_result
my $spoken = $recognizer->final_result();
print $spoken->{text};Returns a hashref containing the recognized text.
Call this method at the end of the input to flush any pending data.
SEE ALSO
Vosk - https://alphacephei.com/vosk/ , https://github.com/alphacep/vosk-api
MODELS
Download pretrained models from