def save_wav_file(filename, wav_data, sample_rate):
"""Saves audio sample data to a .wav audio file.
Args:
filename: Path to save the file to.
wav_data: 2D array of float PCM-encoded audio data.
sample_rate: Samples per second to encode in the file.
"""
with tf.Session(graph=tf.Graph()) as sess:
wav_filename_placeholder = tf.placeholder(tf.string, [])
sample_rate_placeholder = tf.placeholder(tf.int32, [])
wav_data_placeholder = tf.placeholder(tf.float32, [None, 1])
wav_encoder = contrib_audio.encode_wav(wav_data_placeholder,
sample_rate_placeholder)
'''
encode_wav:
Encode audio data using the WAV file format.
This operation will generate a string suitable to be saved out to create a .wav
audio file. It will be encoded in the 16-bit PCM format. It takes in float
values in the range -1.0f to 1.0f, and any outside that value will be clamped to
that range.
'''
wav_saver = io_ops.write_file(wav_filename_placeholder, wav_encoder)
'''
def save_wav_file(filename, wav_data, sample_rate):
with tf.Session(graph=tf.Graph()) as sess:
wav_filename_placeholder = tf.placeholder(tf.string, [])
sample_rate_placeholder = tf.placeholder(tf.int32, [])
wav_data_placeholder = tf.placeholder(tf.float32, [None, 1])
wav_encoder = contrib_audio.encode_wav(wav_data_placeholder,
sample_rate_placeholder)
wav_saver = io_ops.write_file(wav_filename_placeholder, wav_encoder)
sess.run(wav_saver,
feed_dict={
wav_filename_placeholder: filename,
sample_rate_placeholder: sample_rate,
wav_data_placeholder: np.reshape(wav_data, (-1, 1))
})
def save_wav_file(filename, wav_data, sample_rate):
"""Saves audio sample data to a .wav audio file."""
with tf.Session(graph=tf.Graph()) as sess:
wav_filename_placeholder = tf.placeholder(tf.string, [])
sample_rate_placeholder = tf.placeholder(tf.int32, [])
wav_data_placeholder = tf.placeholder(tf.float32, [None, 1])
wav_encoder = contrib_audio.encode_wav(wav_data_placeholder,
sample_rate_placeholder)
wav_saver = io_ops.write_file(wav_filename_placeholder, wav_encoder)
sess.run(
wav_saver,
feed_dict={
wav_filename_placeholder: filename,
sample_rate_placeholder: sample_rate,
wav_data_placeholder: np.reshape(wav_data, (-1, 1))
})
def save_my_test_file(self, model_settings):
desired_samples = model_settings['desired_samples']
self.wav_filename_placeholder_ = tf.placeholder(tf.string, [])
wav_loader = io_ops.read_file(self.wav_filename_placeholder_)
wav_decoder = contrib_audio.decode_wav(
# wav_loader, desired_channels=1, desired_samples=desired_samples)
wav_loader, desired_channels=1, desired_samples=16000)
# Allow the audio sample's volume to be adjusted.
self.foreground_volume_placeholder_ = tf.placeholder(tf.float32, [])
scaled_foreground = tf.multiply(wav_decoder.audio,
self.foreground_volume_placeholder_)
# Shift the sample's start position, and pad any gaps with zeros.
self.time_shift_padding_placeholder_ = tf.placeholder(tf.int32, [2, 2])
self.time_shift_offset_placeholder_ = tf.placeholder(tf.int32, [2])
padded_foreground = tf.pad(
scaled_foreground,
self.time_shift_padding_placeholder_,
mode='CONSTANT')
sliced_foreground = tf.slice(padded_foreground,
self.time_shift_offset_placeholder_,
[desired_samples, -1])
# Mix in background noise.
self.background_data_placeholder_ = tf.placeholder(tf.float32,
[desired_samples, 1])
self.background_volume_placeholder_ = tf.placeholder(tf.float32, [])
background_mul = tf.multiply(self.background_data_placeholder_,
self.background_volume_placeholder_)
background_add = tf.add(background_mul, sliced_foreground)
background_clamp = tf.clip_by_value(background_add, -1.0, 1.0)
self.filename_ = tf.placeholder(tf.string)
# save_wav_file(self.filename_, np.array(background_clamp), 16000)
wav_encoder = contrib_audio.encode_wav(background_clamp,
16000)
self.wav_saver = io_ops.write_file(self.filename_, wav_encoder)
# with tf.Session(graph=tf.Graph()) as sess:
# sess.run(wav_saver)
spectrogram = contrib_audio.audio_spectrogram(
background_clamp,
window_size=model_settings['window_size_samples'],
stride=model_settings['window_stride_samples'],
magnitude_squared=True)
self.test_mfcc_ = contrib_audio.mfcc(
spectrogram,
wav_decoder.sample_rate,
dct_coefficient_count=model_settings['dct_coefficient_count'])
def save_wav(filepath, wav_data, sample_rate=16000):
"""Defines a computational graph that saves an array of floats to a .wav file
Parameters
----------
filepath : a tensor of dtype tf.string and shape (1,) representing the path
of the saved wav file.
wav_data : a tensor of dtype tf.float32 and shape (None, 1) representing
the data to be encoded as a .wav file.
sample_rate : a tensor of type tf.int32 and shape (1,) representing the
desired sample rate at which to encode the data.
Returns
-------
wav_saver : a tensorflow operation that writes the encoded data to a file.
"""
wav_encoder = contrib_audio.encode_wav(data, sample_rate)
wav_saver = io_ops.write_file(filename, wav_encoder)
return wav_saver
def save_wav_file(filename, wav_data, sample_rate):
"""Saves audio sample data to a .wav audio file.
Args:
filename: Path to save the file to.
wav_data: 2D array of float PCM-encoded audio data.
sample_rate: Samples per second to encode in the file.
"""
with tf.Session(graph=tf.Graph()) as sess:
wav_filename_placeholder = tf.placeholder(tf.string, [])
sample_rate_placeholder = tf.placeholder(tf.int32, [])
wav_data_placeholder = tf.placeholder(tf.float32, [None, 1])
wav_encoder = contrib_audio.encode_wav(wav_data_placeholder,
sample_rate_placeholder)
wav_saver = io_ops.write_file(wav_filename_placeholder, wav_encoder)
sess.run(wav_saver,
feed_dict={
wav_filename_placeholder: filename,
sample_rate_placeholder: sample_rate,
wav_data_placeholder: np.reshape(wav_data, (-1, 1))
})
def save_wav_file(filename, wav_data, sample_rate):
"""Saves audio sample data to a .wav audio file.
Args:
filename: Path to save the file to.
wav_data: 2D array of float PCM-encoded audio data.
sample_rate: Samples per second to encode in the file.
"""
with tf.Session(graph=tf.Graph()) as sess:
wav_filename_placeholder = tf.placeholder(tf.string, [])
sample_rate_placeholder = tf.placeholder(tf.int32, [])
wav_data_placeholder = tf.placeholder(tf.float32, [None, 1])
wav_encoder = contrib_audio.encode_wav(wav_data_placeholder,
sample_rate_placeholder)
wav_saver = io_ops.write_file(wav_filename_placeholder, wav_encoder)
sess.run(
wav_saver,
feed_dict={
wav_filename_placeholder: filename,
sample_rate_placeholder: sample_rate,
wav_data_placeholder: np.reshape(wav_data, (-1, 1))
})
def save_wav_file(filename, wav_data, sample_rate):
"""
save audio sample data to a .wav file
input:
filename - file path
wav_data - 2d array of audio data
sample_rate - samples per second
"""
with tf.Session(graph=tf.Graph()) as sess:
wav_filename_placeholder = tf.placeholder(tf.string, [])
sample_rate_placeholder = tf.placeholder(tf.int32, [])
wav_data_placeholder = tf.placeholder(tf.float32, [None, 1])
wav_encoder = contrib_audio.encode_wav(wav_data_placeholder,
sample_rate_placeholder)
wav_saver = io_ops.write_file(wav_filename_placeholder, wav_encoder)
sess.run(wav_saver,
feed_dict={
wav_filename_placeholder: filename,
sample_rate_placeholder: sample_rate,
wav_data_placeholder: np.reshape(wav_data, (-1, 1))
})
def _getWavData(self):
with self.cached_session() as sess:
sample_data = tf.zeros([32000, 2])
wav_encoder = contrib_audio.encode_wav(sample_data, 16000)
wav_data = self.evaluate(wav_encoder)
return wav_data
def _getWavData(self):
with self.test_session() as sess:
sample_data = tf.zeros([1000, 2])
wav_encoder = contrib_audio.encode_wav(sample_data, 16000)
wav_data = sess.run(wav_encoder)
return wav_data
def _getWavData(self):
with self.cached_session() as sess:
sample_data = tf.zeros([32000, 2])
wav_encoder = contrib_audio.encode_wav(sample_data, 16000)
wav_data = self.evaluate(wav_encoder)
return wav_data
def _getWavData(self):
with self.test_session() as sess:
sample_data = tf.zeros([1000, 2])
wav_encoder = contrib_audio.encode_wav(sample_data, 16000)
wav_data = sess.run(wav_encoder)
return wav_data
