I have the code below, which takes an data set(GTZAN) and turns it into an MFCC in dictionary:
DATASET_PATH = '/content/drive/MyDrive/ColabNotebooksNew/PROJECT/ProjectMusic/Data/genres_original'
JSON_PATH = "data_10.json"
SAMPLE_RATE = 22050 #each song is 30s long, with a 22,050 Hz sample rate
TRACK_DURATION = 30 # measured in seconds
SAMPLES_PER_TRACK = SAMPLE_RATE * TRACK_DURATION #=661,500
def save_mfcc(dataset_path, json_path, num_mfcc=13, n_fft=2048, hop_length=512, num_segments=5):
# dictionary to store mapping, labels, and MFCCs
data = {
"mapping": [], #label names. size - (10,)
"labels": [], #Stores the 'real' song type(value from 0-9). size - (5992,)
"mfcc": [] #store the mfccs.size - (5992, 216, 13)
}
samples_per_segment = int(SAMPLES_PER_TRACK / num_segments) #=110250
num_mfcc_vectors_per_segment = math.ceil(samples_per_segment / hop_length) #=216(math.ceil of 215.332)
# loop through all genre sub-folder
for i, (dirpath, dirnames, filenames) in enumerate(os.walk(dataset_path)):
# ensure we're processing a genre sub-folder level
if dirpath is not dataset_path:
# save genre label (i.e., sub-folder name) in the mapping
semantic_label = dirpath.split("/")[-1]
data["mapping"].append(semantic_label)
print("\nProcessing: {}".format(semantic_label))
# process all audio files in genre sub-dir
for f in filenames:
# load audio file
file_path = os.path.join(dirpath, f)
if file_path != '/content/drive/MyDrive/ColabNotebooksNew/PROJECT/ProjectMusic/Data/genres_original/jazz/jazz.00054.wav':
"""fileError: Error opening '/content/drive/MyDrive/ColabNotebooksNew/PROJECT/ProjectMusic/Data/genres_original/jazz/jazz.00054.wav': File contains data in an unknown format."""
signal, sample_rate = librosa.load(file_path, sr=SAMPLE_RATE) #signal= how much samples in the audio file, sample rate = num of sample rate of the audio file, sample=22050
# process all segments of audio file
for d in range(num_segments):
# calculate start and finish sample for current segment
start = samples_per_segment * d
finish = start + samples_per_segment
# extract mfcc
mfcc = librosa.feature.mfcc(signal[start:finish], sample_rate, n_mfcc=num_mfcc, n_fft=n_fft, hop_length=hop_length) #mfcc - time and Coef(13 because num_mfcc=13),
mfcc = mfcc.T #[216,13]
# store only mfcc feature with expected number of vectors
if len(mfcc) == num_mfcc_vectors_per_segment: #==216
data["mfcc"].append(mfcc.tolist())
data["labels"].append(i-1)
print("{}, segment:{}".format(file_path, d+1))
# save MFCCs to json file
with open(json_path, "w") as fp:
json.dump(data, fp, indent=4) #puts everything in the Json File
# Runs Data Processing
save_mfcc(DATASET_PATH, JSON_PATH, num_segments=6)
I have been using this code for a long while, it has worked great until today I got an error as below:
TypeError Traceback (most recent call last)
<ipython-input-10-4a9371926618> in <module>
1 # Runs Data Processing
----> 2 save_mfcc(DATASET_PATH, JSON_PATH, num_segments=6)
<ipython-input-9-8ba1c6e78747> in save_mfcc(dataset_path, json_path, num_mfcc, n_fft, hop_length, num_segments)
56
57 # extract mfcc
---> 58 mfcc = librosa.feature.mfcc(signal[start:finish], sample_rate, n_mfcc=num_mfcc, n_fft=n_fft, hop_length=hop_length) #mfcc - time and Coef(13 because num_mfcc=13),
59 mfcc = mfcc.T #[216,13]
60 # store only mfcc feature with expected number of vectors
TypeError: mfcc() takes 0 positional arguments but 2 positional arguments (and 1 keyword-only argument) were given
About the save_mfcc function:
Extracts MFCCs from music dataset and saves them into a json file along with genre labels.
:param dataset_path (str): Path to dataset
:param json_path (str): Path to json file used to save MFCCs
:param num_mfcc (int): Number of coefficients to extract
:param n_fft (int): Interval we consider to apply FFT. Measured in # of samples
:param hop_length (int): Sliding window for FFT. Measured in # of samples
:param: num_segments (int): Number of segments we want to divide sample tracks into
:return:
I don't understand why the problem just appeared today, and how to fix it.
How can I solve the error?
