aravindpai

history=model.fit([x_tr,y_tr[:,:-1]], y_tr.reshape(y_tr.shape[0],y_tr.shape[1], 1)[:,1:] ,epochs=50,callbacks=[es],batch_size=512, validation_data=([x_val,y_val[:,:-1]], y_val.reshape(y_val.shape[0],y_val.shape[1], 1)[:,1:]))

aravindpai

from matplotlib import pyplot 
pyplot.plot(history.history['loss'], label='train') 
pyplot.plot(history.history['val_loss'], label='test') 
pyplot.legend() pyplot.show()

aravindpai

reverse_target_word_index=y_tokenizer.index_word 
reverse_source_word_index=x_tokenizer.index_word 
target_word_index=y_tokenizer.word_index

aravindpai

# encoder inference
encoder_model = Model(inputs=encoder_inputs,outputs=[encoder_outputs, state_h, state_c])

# decoder inference
# Below tensors will hold the states of the previous time step
decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
decoder_hidden_state_input = Input(shape=(max_len_text,latent_dim))

# Get the embeddings of the decoder sequence

aravindpai

def decode_sequence(input_seq):
    # Encode the input as state vectors.
    e_out, e_h, e_c = encoder_model.predict(input_seq)

    # Generate empty target sequence of length 1.
    target_seq = np.zeros((1,1))

    # Chose the 'start' word as the first word of the target sequence
    target_seq[0, 0] = target_word_index['start']

aravindpai

def seq2summary(input_seq):
    newString=''
    for i in input_seq:
      if((i!=0 and i!=target_word_index['start']) and i!=target_word_index['end']):
        newString=newString+reverse_target_word_index[i]+' '
    return newString

def seq2text(input_seq):
    newString=''
    for i in input_seq:

aravindpai

for i in range(len(x_val)):
  print("Review:",seq2text(x_val[i]))
  print("Original summary:",seq2summary(y_val[i]))
  print("Predicted summary:",decode_sequence(x_val[i].reshape(1,max_len_text)))
  print("\n")

aravindpai

import os
import librosa   #for audio processing
import IPython.display as ipd
import matplotlib.pyplot as plt
import numpy as np
from scipy.io import wavfile #for audio processing
import warnings
warnings.filterwarnings("ignore")

aravindpai

train_audio_path = '../input/tensorflow-speech-recognition-challenge/train/audio/'
samples, sample_rate = librosa.load(train_audio_path+'yes/0a7c2a8d_nohash_0.wav', sr = 16000)
fig = plt.figure(figsize=(14, 8))
ax1 = fig.add_subplot(211)
ax1.set_title('Raw wave of ' + '../input/train/audio/yes/0a7c2a8d_nohash_0.wav')
ax1.set_xlabel('time')
ax1.set_ylabel('Amplitude')
ax1.plot(np.linspace(0, sample_rate/len(samples), sample_rate), samples)

aravindpai

labels=os.listdir(train_audio_path)

#find count of each label and plot bar graph
no_of_recordings=[]
for label in labels:
    waves = [f for f in os.listdir(train_audio_path + '/'+ label) if f.endswith('.wav')]
    no_of_recordings.append(len(waves))
    
#plot
plt.figure(figsize=(30,5))