Ketta/test.py at main · STRTSNM/Ketta · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
#!/usr/bin/env python3

from vosk import Model, KaldiRecognizer
import sys
import json
import os

if not os.path.exists("model"):
    print ("Please download the model from https://alphacephei.com/vosk/models and unpack as 'model' in the current folder.")
    exit (1)


model = Model("model")

# Large vocabulary free form recognition
rec = KaldiRecognizer(model, 16000)

# You can also specify the possible word list
#rec = KaldiRecognizer(model, 16000, "zero oh one two three four five six seven eight nine")

wf = open("speech.mp3", "rb")
wf.read(44) # skip header

while True:
    data = wf.read(4000)
    if len(data) == 0:
        break
    if rec.AcceptWaveform(data):
        res = json.loads(rec.Result())
        print (res['text'])

res = json.loads(rec.FinalResult())
comm = str(res['text'][0])
print (res['text'])
if "chrome" in comm:
    os.system("google-chrome-stable")
if comm != "":
    print("audio is not empty")
    os.system("python pec_audio.py")

print("recognition done")