Created
November 25, 2022 11:13
-
-
Save pteacher/6789ff3009621fa131f2e8f8d9db3a49 to your computer and use it in GitHub Desktop.
Python voice recognition using vosk for Turkish language
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import wave | |
from vosk import Model, KaldiRecognizer | |
import json | |
import librosa | |
import soundfile as sf | |
def get_text_from_voice(filename): | |
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) | |
x,_ = librosa.load(filename, sr=16000) | |
sf.write('tmp.wav', x, 16000) | |
wf = wave.open('tmp.wav', "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("model") | |
rec = KaldiRecognizer(model, wf.getframerate()) | |
rec.SetWords(True) | |
text_lst =[] | |
p_text_lst = [] | |
p_str = [] | |
len_p_str = [] | |
txt = [""] | |
id = 0 | |
while True: | |
data = wf.readframes(4000) | |
if len(data) == 0: | |
break | |
if rec.AcceptWaveform(data): | |
text_lst.append(rec.Result()) | |
print(rec.Result()) | |
id += 1 | |
txt.append("") | |
else: | |
p_text_lst.append(rec.PartialResult()) | |
p = json.loads(rec.PartialResult())["partial"] | |
txt[id] = p | |
# print(p) | |
if len(text_lst) !=0: | |
jd = json.loads(text_lst[0]) | |
txt_str = jd["text"] | |
elif len(p_text_lst) !=0: | |
for i in range(0,len(p_text_lst)): | |
temp_txt_dict = json.loads(p_text_lst[i]) | |
p_str.append(temp_txt_dict['partial']) | |
len_p_str = [len(p_str[j]) for j in range(0,len(p_str))] | |
max_val = max(len_p_str) | |
indx = len_p_str.index(max_val) | |
txt_str = p_str[indx] | |
print(txt_str) | |
txt.append(txt_str) | |
else: | |
txt_str ='' | |
return ". ".join(txt) | |
res = get_text_from_voice("test.ogg") | |
print(res) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment