-
Notifications
You must be signed in to change notification settings - Fork 0
/
audiobase.py
269 lines (214 loc) · 8.98 KB
/
audiobase.py
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
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
from logging.config import listen
import os
import wave
import pickle
import pyaudio
import warnings
import numpy as np
from sklearn import preprocessing
from scipy.io.wavfile import read
import python_speech_features as mfcc
from sklearn.mixture import GaussianMixture
from listen import *
from time import time
import speech_recognition as sr
import playsound
from gtts import gTTS
from test import *
from train import *
from questions import *
warnings.filterwarnings("ignore")
r = sr.Recognizer()
def speak(text):
tts = gTTS(text = text, lang = "en")
filename = "voice.mp3"
tts.save(filename)
playsound.playsound(filename)
os.remove(filename)
#Starting here
speak("Hello Student! Are you ready?")
response = listener()
print("response recieved")
if "yes" in response:
print(response)
record_audio_train()
speak("Getting your voice model ready. Please wait")
train_model()
speak("Talk for auth")
print("hereeeeee")
record_audio_test()
test_model()
speak("Test starts now")
mcq_for_test()
else:
speak("Okay, run this application when you are ready")
# def calculate_delta(array):
# rows,cols = array.shape
# print(rows)
# print(cols)
# deltas = np.zeros((rows,20))
# N = 2
# for i in range(rows):
# index = []
# j = 1
# while j <= N:
# if i-j < 0:
# first =0
# else:
# first = i-j
# if i+j > rows-1:
# second = rows-1
# else:
# second = i+j
# index.append((second,first))
# j+=1
# deltas[i] = ( array[index[0][0]]-array[index[0][1]] + (2 * (array[index[1][0]]-array[index[1][1]])) ) / 10
# return deltas
# def extract_features(audio,rate):
# mfcc_feature = mfcc.mfcc(audio,rate, 0.025, 0.01,20,nfft = 1200, appendEnergy = True)
# mfcc_feature = preprocessing.scale(mfcc_feature)
# print(mfcc_feature)
# delta = calculate_delta(mfcc_feature)
# combined = np.hstack((mfcc_feature,delta))
# return combined
# def record_audio_train():
# speak("Please Speak Your Name:")
# #Name =(input("Please Enter Your Name:")
# with sr.Microphone() as source:
# print("Speak:")
# aud = r.listen(source)
# Name = r.recognize_google(aud)
# Ques = ["How are you?", "State your class and course","State your roll number","Repeat this line 3 times: Red blood, Blue blood","Any final words?"]
# for count in range(5):
# FORMAT = pyaudio.paInt16
# CHANNELS = 1
# RATE = 44100
# CHUNK = 512
# RECORD_SECONDS = 8
# device_index = 2
# audio = pyaudio.PyAudio()
# print("----------------------record device list---------------------")
# info = audio.get_host_api_info_by_index(0)
# numdevices = info.get('deviceCount')
# for i in range(0, numdevices):
# if (audio.get_device_info_by_host_api_device_index(0, i).get('maxInputChannels')) > 0:
# print("Input Device id ", i, " - ", audio.get_device_info_by_host_api_device_index(0, i).get('name'))
# print("-------------------------------------------------------------")
# index = int(input())
# print("recording via index "+str(index))
# print(Ques[count])
# speak(Ques[count])
# stream = audio.open(format=FORMAT, channels=CHANNELS,
# rate=RATE, input=True,input_device_index = index,
# frames_per_buffer=CHUNK)
# print ("recording started")
# Recordframes = []
# for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
# data = stream.read(CHUNK)
# Recordframes.append(data)
# print ("recording stopped")
# stream.stop_stream()
# stream.close()
# audio.terminate()
# OUTPUT_FILENAME=Name+"-sample"+str(count)+".wav"
# WAVE_OUTPUT_FILENAME=os.path.join("training_set",OUTPUT_FILENAME)
# trainedfilelist = open("training_set_addition.txt", 'a')
# trainedfilelist.write(OUTPUT_FILENAME+"\n")
# waveFile = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
# waveFile.setnchannels(CHANNELS)
# waveFile.setsampwidth(audio.get_sample_size(FORMAT))
# waveFile.setframerate(RATE)
# waveFile.writeframes(b''.join(Recordframes))
# waveFile.close()
# def record_audio_test():
# FORMAT = pyaudio.paInt16
# CHANNELS = 1
# RATE = 44100
# CHUNK = 512
# RECORD_SECONDS = 10
# device_index = 2
# audio = pyaudio.PyAudio()
# print("----------------------record device list---------------------")
# info = audio.get_host_api_info_by_index(0)
# numdevices = info.get('deviceCount')
# for i in range(0, numdevices):
# if (audio.get_device_info_by_host_api_device_index(0, i).get('maxInputChannels')) > 0:
# print("Input Device id ", i, " - ", audio.get_device_info_by_host_api_device_index(0, i).get('name'))
# print("-------------------------------------------------------------")
# index = int(input())
# print("recording via index "+str(index))
# stream = audio.open(format=FORMAT, channels=CHANNELS,
# rate=RATE, input=True,input_device_index = index,
# frames_per_buffer=CHUNK)
# print ("recording started")
# Recordframes = []
# for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
# data = stream.read(CHUNK)
# Recordframes.append(data)
# print ("recording stopped")
# stream.stop_stream()
# stream.close()
# audio.terminate()
# OUTPUT_FILENAME="sample.wav"
# WAVE_OUTPUT_FILENAME=os.path.join("testing_set",OUTPUT_FILENAME)
# trainedfilelist = open("testing_set_addition.txt", 'a')
# trainedfilelist.write(OUTPUT_FILENAME+"\n")
# waveFile = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
# waveFile.setnchannels(CHANNELS)
# waveFile.setsampwidth(audio.get_sample_size(FORMAT))
# waveFile.setframerate(RATE)
# waveFile.writeframes(b''.join(Recordframes))
# waveFile.close()
# def train_model():
# source = "C:\\Users\\marka\\Desktop\\Programming\\Hackathon project\\Speaker-Identification\\training_set\\"
# dest = "C:\\Users\\marka\\Desktop\\Programming\\Hackathon project\\Speaker-Identification\\trained_models"
# train_file = "C:\\Users\\marka\\Desktop\\Programming\\Hackathon project\\Speaker-Identification\\training_set_addition.txt"
# file_paths = open(train_file,'r')
# count = 1
# features = np.asarray(())
# for path in file_paths:
# path = path.strip()
# print(path)
# sr,audio = read(source + path)
# print(sr)
# vector = extract_features(audio,sr)
# if features.size == 0:
# features = vector
# else:
# features = np.vstack((features, vector))
# if count == 5:
# gmm = GaussianMixture(n_components = 6, max_iter = 200, covariance_type='diag',n_init = 3)
# gmm.fit(features)
# # dumping the trained gaussian model
# picklefile = path.split("-")[0]+".gmm"
# pickle.dump(gmm,open(dest + picklefile,'wb'))
# print('+ modeling completed for speaker:',picklefile," with data point = ",features.shape)
# features = np.asarray(())
# count = 0
# count = count + 1
# def test_model():
# source = "C:\\Users\\marka\\Desktop\\Programming\\Hackathon project\\Speaker-Identification\\testing_set\\"
# modelpath = "C:\\Users\\marka\\Desktop\\Programming\\Hackathon project\\Speaker-Identification\\trained_models"
# test_file = "C:\\Users\\marka\\Desktop\\Programming\\Hackathon project\\Speaker-Identification\\testing_set_addition.txt"
# file_paths = open(test_file,'r')
# gmm_files = [os.path.join(modelpath,fname) for fname in os.listdir(modelpath) if fname.endswith('.gmm')]
# #gmm_files = ["C:\\Users\\marka\\Desktop\\Programming\\Hackathon project\\trained_modelsMark.gmm","C:\\Users\\marka\\Desktop\\Programming\\Hackathon project\\trained_modelsNeha.gmm","C:\\Users\\marka\\Desktop\\Programming\\Hackathon project\\trained_modelsCrazy.gmm"]
# #Load the Gaussian gender Models
# models = [pickle.load(open(fname,'rb')) for fname in gmm_files]
# speakers = [fname.split("\\")[-1].split(".gmm")[0] for fname in gmm_files]
# # Read the test directory and get the list of test audio files
# for path in file_paths:
# path = path.strip()
# # print(path)
# sr,audio = read(source + path)
# vector = extract_features(audio,sr)
# log_likelihood = np.zeros(len(models))
# for i in range(len(models)):
# gmm = models[i] #checking with each model one by one
# scores = np.array(gmm.score(vector))
# log_likelihood[i] = scores.sum()
# winner = np.argmax(log_likelihood)
# print("\tdetected as - ", speakers[winner])
# time.sleep(1.0)
#choice=int(input("\n1.Record audio for training \n 2.Train Model \n 3.Record audio for testing \n 4.Test Model\n"))
#Function for MCQ loop(snap, take test sample, test model)