def main(unused_argv):
logging.set_verbosity(FLAGS.log)
if not os.path.exists(FLAGS.output_dir):
os.makedirs(FLAGS.output_dir)
for input_file in sorted(os.listdir(FLAGS.input_dir)):
if not input_file.endswith('.wav'):
continue
wav_filename = input_file
midi_filename = input_file.replace('.wav', '.mid')
logging.info('Aligning %s to %s', midi_filename, wav_filename)
samples = audio_io.load_audio(
os.path.join(FLAGS.input_dir, wav_filename),
align_fine_lib.SAMPLE_RATE)
ns = midi_io.midi_file_to_sequence_proto(
os.path.join(FLAGS.input_dir, midi_filename))
aligned_ns, unused_stats = align_fine_lib.align_cpp(
samples,
align_fine_lib.SAMPLE_RATE,
ns,
align_fine_lib.CQT_HOP_LENGTH_FINE,
sf2_path=FLAGS.sf2_path,
penalty_mul=FLAGS.penalty_mul)
midi_io.sequence_proto_to_midi_file(
aligned_ns, os.path.join(FLAGS.output_dir, midi_filename))
logging.info('Done')
def generate_test_set():
"""Generate the test TFRecord."""
test_file_pairs = []
for directory in test_dirs:
path = os.path.join(FLAGS.input_dir, directory)
path = os.path.join(path, '*.wav')
wav_files = glob.glob(path)
# find matching mid files
for wav_file in wav_files:
base_name_root, _ = os.path.splitext(wav_file)
mid_file = base_name_root + '.mid'
test_file_pairs.append((wav_file, mid_file))
test_output_name = os.path.join(FLAGS.output_dir,
'maps_config2_test.tfrecord')
with tf.python_io.TFRecordWriter(test_output_name) as writer:
for idx, pair in enumerate(test_file_pairs):
print('{} of {}: {}'.format(idx, len(test_file_pairs), pair[0]))
# load the wav data and resample it.
samples = audio_io.load_audio(pair[0], FLAGS.sample_rate)
wav_data = audio_io.samples_to_wav_data(samples, FLAGS.sample_rate)
# load the midi data and convert to a notesequence
ns = midi_io.midi_file_to_note_sequence(pair[1])
example = audio_label_data_utils.create_example(
pair[0], ns, wav_data)
writer.write(example.SerializeToString())
return [filename_to_id(wav) for wav, _ in test_file_pairs]
def main(unused_argv):
logging.set_verbosity(FLAGS.log)
if not os.path.exists(FLAGS.output_dir):
os.makedirs(FLAGS.output_dir)
for input_file in sorted(os.listdir(FLAGS.input_dir)):
if not input_file.endswith('.wav'):
continue
wav_filename = input_file
midi_filename = input_file.replace('.wav', '.mid')
logging.info('Aligning %s to %s', midi_filename, wav_filename)
samples = audio_io.load_audio(
os.path.join(FLAGS.input_dir, wav_filename), align_fine_lib.SAMPLE_RATE)
ns = midi_io.midi_file_to_sequence_proto(
os.path.join(FLAGS.input_dir, midi_filename))
aligned_ns, unused_stats = align_fine_lib.align_cpp(
samples,
align_fine_lib.SAMPLE_RATE,
ns,
align_fine_lib.CQT_HOP_LENGTH_FINE,
sf2_path=FLAGS.sf2_path,
penalty_mul=FLAGS.penalty_mul)
midi_io.sequence_proto_to_midi_file(
aligned_ns, os.path.join(FLAGS.output_dir, midi_filename))
logging.info('Done')
def generate_test_set():
"""Generate the test TFRecord."""
test_file_pairs = []
for directory in test_dirs:
path = os.path.join(FLAGS.input_dir, directory)
path = os.path.join(path, '*.wav')
wav_files = glob.glob(path)
# find matching mid files
for wav_file in wav_files:
base_name_root, _ = os.path.splitext(wav_file)
mid_file = base_name_root + '.mid'
test_file_pairs.append((wav_file, mid_file))
test_output_name = os.path.join(FLAGS.output_dir,
'maps_config2_test.tfrecord')
with tf.python_io.TFRecordWriter(test_output_name) as writer:
for idx, pair in enumerate(test_file_pairs):
print('{} of {}: {}'.format(idx, len(test_file_pairs), pair[0]))
# load the wav data and resample it.
samples = audio_io.load_audio(pair[0], FLAGS.sample_rate)
wav_data = audio_io.samples_to_wav_data(samples, FLAGS.sample_rate)
# load the midi data and convert to a notesequence
ns = midi_io.midi_file_to_note_sequence(pair[1])
example = split_audio_and_label_data.create_example(pair[0], ns, wav_data)
writer.write(example.SerializeToString())
return [filename_to_id(wav) for wav, _ in test_file_pairs]
def generate_test_set():
"""Generate the test TFRecord."""
test_file_pairs = []
for directory in test_dirs:
path = os.path.join(FLAGS.input_dir, directory)
path = os.path.join(path, '*.wav')
wav_files = glob.glob(path)
# find matching mid files
for wav_file in wav_files:
base_name_root, _ = os.path.splitext(wav_file)
mid_file = base_name_root + '.mid'
test_file_pairs.append((wav_file, mid_file))
test_output_name = os.path.join(FLAGS.output_dir,
'maps_config2_test.tfrecord')
with tf.python_io.TFRecordWriter(test_output_name) as writer:
for pair in test_file_pairs:
print(pair)
# load the wav data and resample it.
samples = audio_io.load_audio(pair[0], FLAGS.sample_rate)
wav_data = audio_io.samples_to_wav_data(samples, FLAGS.sample_rate)
# load the midi data and convert to a notesequence
midi_data = tf.gfile.Open(pair[1]).read()
ns = midi_io.midi_to_sequence_proto(midi_data)
velocities = [note.velocity for note in ns.notes]
velocity_max = np.max(velocities)
velocity_min = np.min(velocities)
new_velocity_tuple = music_pb2.VelocityRange(
min=velocity_min, max=velocity_max)
example = tf.train.Example(features=tf.train.Features(feature={
'id':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[pair[0]]
)),
'sequence':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[ns.SerializeToString()]
)),
'audio':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[wav_data]
)),
'velocity_range':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[new_velocity_tuple.SerializeToString()]
)),
}))
writer.write(example.SerializeToString())
return [filename_to_id(wav) for wav, _ in test_file_pairs]
def generate_test_set():
"""Generate the test TFRecord."""
test_file_pairs = []
for directory in test_dirs:
path = os.path.join(FLAGS.input_dir, directory)
path = os.path.join(path, '*.wav')
wav_files = glob.glob(path)
# find matching mid files
for wav_file in wav_files:
base_name_root, _ = os.path.splitext(wav_file)
mid_file = base_name_root + '.mid'
test_file_pairs.append((wav_file, mid_file))
test_output_name = os.path.join(FLAGS.output_dir,
'maps_config2_test.tfrecord')
with tf.python_io.TFRecordWriter(test_output_name) as writer:
for pair in test_file_pairs:
print(pair)
# load the wav data and resample it.
samples = audio_io.load_audio(pair[0], FLAGS.sample_rate)
wav_data = audio_io.samples_to_wav_data(samples, FLAGS.sample_rate)
# load the midi data and convert to a notesequence
midi_data = tf.gfile.Open(pair[1]).read()
ns = midi_io.midi_to_sequence_proto(midi_data)
velocities = [note.velocity for note in ns.notes]
velocity_max = np.max(velocities)
velocity_min = np.min(velocities)
new_velocity_tuple = music_pb2.VelocityRange(
min=velocity_min, max=velocity_max)
example = tf.train.Example(features=tf.train.Features(feature={
'id':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[pair[0]]
)),
'sequence':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[ns.SerializeToString()]
)),
'audio':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[wav_data]
)),
'velocity_range':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[new_velocity_tuple.SerializeToString()]
)),
}))
writer.write(example.SerializeToString())
return [filename_to_id(wav) for wav, _ in test_file_pairs]