def run(inputs, output_dir=None, suffix=None, input_repr="mel256", content_type="music",
embedding_size=6144, center=True, hop_size=0.1, verbose=False):
"""
Computes and saves L3 embedding for given inputs.
Parameters
----------
inputs : list of str, or str
File/directory path or list of file/directory paths to be processed
output_dir : str or None
Path to directory for saving output files. If None, output files will
be saved to the directory containing the input file.
suffix : str or None
String to be appended to the output filename, i.e. <base filename>_<suffix>.npy.
If None, then no suffix will be added, i.e. <base filename>.npy.
input_repr : "linear", "mel128", or "mel256"
Spectrogram representation used for model.
content_type : "music" or "env"
Type of content used to train embedding.
embedding_size : 6144 or 512
Embedding dimensionality.
center : boolean
If True, pads beginning of signal so timestamps correspond
to center of window.
hop_size : float
Hop size in seconds.
quiet : boolean
If True, suppress all non-error output to stdout
Returns
-------
"""
if isinstance(inputs, string_types):
file_list = [inputs]
elif isinstance(inputs, Iterable):
file_list = get_file_list(inputs)
else:
raise OpenL3Error('Invalid input: {}'.format(str(inputs)))
if len(file_list) == 0:
print('openl3: No WAV files found in {}. Aborting.'.format(str(inputs)))
sys.exit(-1)
# Load model
model = load_embedding_model(input_repr, content_type, embedding_size)
# Process all files in the arguments
for filepath in file_list:
if verbose:
print('openl3: Processing: {}'.format(filepath))
process_file(filepath,
output_dir=output_dir,
suffix=suffix,
model=model,
center=center,
hop_size=hop_size,
verbose=verbose)
if verbose:
print('openl3: Done!')
def embedFiles(datasetPath, newDir):
soundfiles = urbansound8k.load_dataset()
model = openl3.models.load_embedding_model(input_repr="mel256", content_type="env",
embedding_size=512)
for index in range(len(soundfiles)):
sample = soundfiles.iloc[index, :] #fetch each sample from the dataset
path = urbansound8k.sample_path(sample,datasetPath) #find the path given the sample, and the directory the files lay in.
fold = sample["fold"] #get the fold for the sound from the sample
differentDir = newDir+str(fold) #assign directory to save file in by adding the respective fold to the path
openl3.process_file(path, suffix=None, output_dir=differentDir,model=model, content_type="env", embedding_size=512, hop_size=0.5, verbose=True) #save the embedded file in its respective fold in the differentDir directory
def test_process_file():
test_output_dir = tempfile.mkdtemp()
test_subdir = os.path.join(test_output_dir, "subdir")
os.makedirs(test_subdir)
# Make a copy of the file so we can test the case where we save to the same directory
input_path_alt = os.path.join(test_subdir, "chirp_mono.wav")
shutil.copy(CHIRP_MONO_PATH, test_subdir)
invalid_file_path = os.path.join(test_subdir, "invalid.wav")
with open(invalid_file_path, 'w') as f:
f.write('This is not an audio file.')
exp_output_path1 = os.path.join(test_output_dir, "chirp_mono.npz")
exp_output_path2 = os.path.join(test_output_dir, "chirp_mono_suffix.npz")
exp_output_path3 = os.path.join(test_subdir, "chirp_mono.npz")
try:
openl3.process_file(CHIRP_MONO_PATH, output_dir=test_output_dir)
openl3.process_file(CHIRP_MONO_PATH,
output_dir=test_output_dir,
suffix='suffix')
openl3.process_file(input_path_alt)
# Make sure we fail when invalid files are provided
pytest.raises(OpenL3Error, openl3.process_file, invalid_file_path)
# Make sure paths all exist
assert os.path.exists(exp_output_path1)
assert os.path.exists(exp_output_path2)
assert os.path.exists(exp_output_path3)
data = np.load(exp_output_path1)
assert 'embedding' in data
assert 'timestamps' in data
embedding = data['embedding']
timestamps = data['timestamps']
# Quick sanity check on data
assert embedding.ndim == 2
assert timestamps.ndim == 1
# Make sure that suffices work
finally:
shutil.rmtree(test_output_dir)
# Make sure we fail when file cannot be opened
pytest.raises(OpenL3Error, openl3.process_file, '/fake/directory/asdf.wav')