malar
/
speech-scoring
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

implemented tfrecord writer for spectrograms

master
Malar Kannan 2017-11-06 14:12:09 +05:30
parent fabd882664
commit c187fbe1ca
1 changed files with 26 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
speech_data.py
View File

@ -1,7 +1,8 @@
import pandas as pd import pandas as pd
from pandas_parallel import apply_by_multiprocessing from pandas_parallel import apply_by_multiprocessing
import dask as dd # import dask as dd
import dask.dataframe as ddf # import dask.dataframe as ddf
import tensorflow as tf
import numpy as np import numpy as np
from spectro_gen import generate_aiff_spectrogram from spectro_gen import generate_aiff_spectrogram
from sklearn.model_selection import train_test_split from sklearn.model_selection import train_test_split
@ -91,13 +92,14 @@ def create_spectrogram_data(audio_group='audio'):
audio_samples.to_pickle('outputs/{}-spectrogram.pkl'.format(audio_group)) audio_samples.to_pickle('outputs/{}-spectrogram.pkl'.format(audio_group))
def create_spectrogram_tfrecords(audio_group='audio'): def create_spectrogram_tfrecords(audio_group='audio'):
# audio_group = 'story_words'
audio_samples = pd.read_csv( './outputs/' + audio_group + '.csv' audio_samples = pd.read_csv( './outputs/' + audio_group + '.csv'
, names=['word','phonemes', 'voice', 'language', 'rate', 'variant', 'file'] , names=['word','phonemes', 'voice', 'language', 'rate', 'variant', 'file']
, quoting=csv.QUOTE_NONE) , quoting=csv.QUOTE_NONE)
# audio_samples = audio_samples.loc[audio_samples['word'] == # audio_samples = audio_samples.loc[audio_samples['word'] ==
# 'sunflowers'].reset_index(drop=True) # 'sunflowers'].reset_index(drop=True)
audio_samples['file_paths'] = audio_samples.loc[:, 'file'].apply(lambda x: 'outputs/' + audio_group + '/' + x) audio_samples['file_path'] = audio_samples.loc[:, 'file'].apply(lambda x: 'outputs/' + audio_group + '/' + x)
audio_samples['file_exists'] = apply_by_multiprocessing(audio_samples['file_paths'], os.path.exists) audio_samples['file_exists'] = apply_by_multiprocessing(audio_samples['file_path'], os.path.exists)
audio_samples = audio_samples[audio_samples['file_exists'] == True].reset_index() audio_samples = audio_samples[audio_samples['file_exists'] == True].reset_index()
# audio_samples['spectrogram'] = apply_by_multiprocessing(audio_samples['file_paths'],generate_aiff_spectrogram)#.apply( # audio_samples['spectrogram'] = apply_by_multiprocessing(audio_samples['file_paths'],generate_aiff_spectrogram)#.apply(
# audio_samples['window_count'] = audio_samples.loc[:,'spectrogram'].apply(lambda x: x.shape[0]) # audio_samples['window_count'] = audio_samples.loc[:,'spectrogram'].apply(lambda x: x.shape[0])
@ -111,17 +113,29 @@ def create_spectrogram_tfrecords(audio_group='audio'):
def _bytes_feature(value): def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=value)) return tf.train.Feature(bytes_list=tf.train.BytesList(value=value))
writer = tf.python_io.TFRecordWriter(output_path)
for sample in audio_samples: writer = tf.python_io.TFRecordWriter('./outputs/' + audio_group + '.tfrecords')
audio_samples = audio_samples[:100]
for (i,sample) in audio_samples.iterrows():
spectrogram = generate_aiff_spectrogram(sample['file_path'])
spec_n = spectrogram.shape[0]
spec_w = spectrogram.shape[1]
spec = spectrogram.reshape(-1)
example = tf.train.Example(features=tf.train.Features( example = tf.train.Example(features=tf.train.Features(
feature={ feature={
'label': _int64_feature([label]), 'word': _bytes_feature([sample['word'].encode('utf-8')]),
'path': _bytes_feature([image_path]), 'phoneme': _bytes_feature([sample['phonemes'].encode('utf-8')]),
'instance' : _bytes_feature([instance_id]) 'voice': _bytes_feature([sample['voice'].encode('utf-8')]),
'language': _bytes_feature([sample['language'].encode('utf-8')]),
'rate':_int64_feature([sample['rate']]),
'variant': _bytes_feature([sample['variant'].encode('utf-8')]),
'file': _bytes_feature([sample['file'].encode('utf-8')]),
'spec':_float_feature(spec),
'spec_n':_int64_feature([spec_n]),
'spec_w':_int64_feature([spec_w])
} }
)) ))
writer.write(example.SerializeToString()) writer.write(example.SerializeToString())
writer.close() writer.close()
def create_tagged_data(audio_samples): def create_tagged_data(audio_samples):
@ -177,7 +191,8 @@ def speech_model_data():
if __name__ == '__main__': if __name__ == '__main__':
# sunflower_pairs_data() # sunflower_pairs_data()
# create_spectrogram_data() # create_spectrogram_data()
create_spectrogram_data('story_words') # create_spectrogram_data('story_words')
create_spectrogram_tfrecords('story_words')
# create_padded_spectrogram() # create_padded_spectrogram()
# create_speech_pairs_data() # create_speech_pairs_data()
# print(speech_model_data()) # print(speech_model_data())