aravindpai

duration_of_recordings=[]
for label in labels:
    waves = [f for f in os.listdir(train_audio_path + '/'+ label) if f.endswith('.wav')]
    for wav in waves:
        sample_rate, samples = wavfile.read(train_audio_path + '/' + label + '/' + wav)
        duration_of_recordings.append(float(len(samples)/sample_rate))
    
plt.hist(np.array(duration_of_recordings))

aravindpai

train_audio_path = '../input/tensorflow-speech-recognition-challenge/train/audio/'

all_wave = []
all_label = []
for label in labels:
    print(label)
    waves = [f for f in os.listdir(train_audio_path + '/'+ label) if f.endswith('.wav')]
    for wav in waves:
        samples, sample_rate = librosa.load(train_audio_path + '/' + label + '/' + wav, sr = 16000)
        samples = librosa.resample(samples, sample_rate, 8000)

aravindpai

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
y=le.fit_transform(all_label)
classes= list(le.classes_)

aravindpai

from keras.layers import Dense, Dropout, Flatten, Conv1D, Input, MaxPooling1D
from keras.models import Model
from keras.callbacks import EarlyStopping, ModelCheckpoint
from keras import backend as K
K.clear_session()

inputs = Input(shape=(8000,1))

#First Conv1D layer
conv = Conv1D(8,13, padding='valid', activation='relu', strides=1)(inputs)

aravindpai

def predict(audio):
    prob=model.predict(audio.reshape(1,8000,1))
    index=np.argmax(prob[0])
    return classes[index]

aravindpai

import random
index=random.randint(0,len(x_val)-1)
samples=x_val[index].ravel()
print("Audio:",classes[np.argmax(y_val[index])])
ipd.Audio(samples, rate=8000)
print("Text:",predict(samples))

aravindpai

import sounddevice as sd
import soundfile as sf

samplerate = 16000  
duration = 1 # seconds
filename = 'yes.wav'
print("start")
mydata = sd.rec(int(samplerate * duration), samplerate=samplerate,
    channels=1, blocking=True)
print("end")

aravindpai

os.listdir('../input/voice-commands/prateek_voice_v2')
filepath='../input/voice-commands/prateek_voice_v2'

#reading the voice commands
samples, sample_rate = librosa.load(filepath + '/' + 'stop.wav', sr = 16000)
samples = librosa.resample(samples, sample_rate, 8000)
ipd.Audio(samples,rate=8000)  

predict(samples)

aravindpai

import pandas as pd
df=pd.DataFrame(columns=['energy','start','end'])
thresh=12000
row_index=0
for i in range(len(energy)):
  value=energy[i]
  if(value>=thresh):
    i=np.where(energy == value)[0]
    df.loc[row_index,'energy']=value
    df.loc[row_index,'start']=i[0] * 5

aravindpai

temp=[]
i=0
j=0
n=len(df) - 2
m=len(df) - 1
while(i<=n):
  j=i+1
  while(j<=m):
    if(df['end'][i] == df['start'][j]):
      df.loc[i,'end'] = df.loc[j,'end']