#!/usr/bin/env python3

from vosk import Model, KaldiRecognizer, SetLogLevel
import sys
import os
import wave

SetLogLevel(0)

wf = wave.open(sys.argv[1], "rb")
if wf.getnchannels() != 1 or wf.getsampwidth() != 2 or wf.getcomptype() != "NONE":
    print ("Audio file must be WAV format mono PCM.")
    exit (1)

model = Model(lang="en-us")
rec = KaldiRecognizer(model, wf.getframerate())
rec.SetMaxAlternatives(10)
rec.SetNLSML(True)

while True:
    data = wf.readframes(4000)
    if len(data) == 0:
        break
    if rec.AcceptWaveform(data):
        print(rec.Result())

print(rec.FinalResult())