def Augmented_Spectrograms(WIDTH, HEIGHT, DPI, SONG_DURATION, SR):
directory = './AugmentedData'
tracks = utils.load('./fma_metadata/tracks.csv')
#STARTING ID BE SURE TO MAKE SURE NO CONFLICTS
augmented_id = 200000
for subdir, dirs, files in os.walk(directory):
path_list = subdir.split(os.sep)
for file in files:
full_path = os.path.join(subdir, file)
name = os.path.splitext(os.path.basename(file))
id = name[0]
if (tracks['set', 'split'][int(id)] == "training"):
new_row = [augmented_id, tracks['track', 'genre_top'][int(id)]]
create_spectrogram(full_path, str(augmented_id), "train",
WIDTH, HEIGHT, DPI, SR)
append_list_as_row('./Data/train.csv', new_row)
augmented_id += 1
def mp3_Convert(num_files_to_convert):
AUDIO_DIR = './fma_small/'
tracks = utils.load('./fma_metadata/tracks.csv')
try:
os.mkdir('Samples')
except:
print("Sample Folder Exists. No Creation Necessary")
small = tracks['set', 'subset'] <= 'small'
y_small = tracks.loc[small, ('track', 'genre_top')]
sr = 44100
file_count = 0
for track_id, genre in y_small.iteritems():
if not os.path.exists('Samples/'+genre):
os.mkdir('Samples/'+genre)
mp3_filename = utils.get_audio_path(AUDIO_DIR, track_id)
out_wav_filename = 'Samples/'+genre+'/'+str(track_id)+'.wav'
in_wav_filename = out_wav_filename
cmd = 'ffmpeg -hide_banner -loglevel panic -i ' + mp3_filename + ' ' + in_wav_filename
print("excuting conversion: "+cmd)
try:
os.system(cmd)
except:
print("Could not find file:" + mp3_filename)
continue
# os.system(cmd) - we use subprocess instead of this
## We could just have ffmpeg do the full conversion, but we'll let librosa
## apply its own defaults by reading & writing
print("reading ",in_wav_filename)
try:
data, sr = librosa.load(in_wav_filename, sr=sr, mono=True)
except:
print("Failed reading the converted in_wav:" + in_wav_filename)
continue
print("writing ",out_wav_filename)
try:
librosa.output.write_wav(out_wav_filename,data,sr=sr)
except:
print("failed writing the output_wav:"+out_wav_filename)
continue
file_count += 1
if file_count > num_files_to_convert:
break
print(".mp3 file conversion to .wav complete")
def Generate_CSV():
print("Begin CSV generation")
tracks = utils.load('./fma_metadata/tracks.csv')
#genres = utils.load('./fma_metadata/genres.csv')
#features = utils.load('./fma_metadata/features.csv')
#echonest = utils.load('./fma_metadata/echonest.csv')
#print(tracks['track', 'genre_top'][1482])
try:
os.mkdir("Data")
except:
print("Data folder exists, skip creation")
#Creating a list of ids that are in FMA_SMALL, so that we only create a csv file for data we have
fma_small_track_id = []
directory = './Data'
for subdir, dirs, files in os.walk(directory):
for file in files:
name = os.path.splitext(os.path.basename(file))
id = name[0]
fma_small_track_id.append(id)
data_top = tracks['set', 'split'].head(len(tracks['set', 'split']))
df_train = pd.DataFrame(columns=['ID', 'Genre'])
df_validation = pd.DataFrame(columns=['ID', 'Genre'])
df_test = pd.DataFrame(columns=['ID', 'Genre'])
for id in data_top.index:
if str(id) in fma_small_track_id:
# if(tracks['set', 'split'][id] == "training"):
# print("Adding Training Data", id)
# df_train = df_train.append({'ID': id, 'Genre': tracks['track', 'genre_top'][id]}, ignore_index = True)
if(tracks['set', 'split'][id] == "test"):
print("Adding Testing Data", id)
df_test = df_test.append({'ID': id, 'Genre': tracks['track', 'genre_top'][id]}, ignore_index = True)
elif(tracks['set', 'split'][id] == "training"):
print("Adding Training Data", id)
df_train = df_train.append({'ID': id, 'Genre': tracks['track', 'genre_top'][id]}, ignore_index = True)
else:
print("Adding Validation Data", id)
df_validation= df_validation.append({'ID': id, 'Genre': tracks['track', 'genre_top'][id]}, ignore_index = True)
df_train.to_csv('Data/train.csv', encoding='utf-8', index= False, header=False)
df_validation.to_csv('Data/validate.csv', encoding='utf-8', index= False, header=False)
df_test.to_csv('Data/test.csv', encoding='utf-8', index= False, header=False)
print("Completed CSV generation, check the ./Data folder for your .csv")
def Tempo_Change_Convert(tempo):
AUDIO_DIR = './Samples/'
tracks = utils.load('./fma_metadata/tracks.csv')
try:
os.mkdir('./AugmentedData/Tempo')
except:
print("Tempo Folder Exists. No Creation Necessary")
for subdir, dirs, files in os.walk(AUDIO_DIR):
path_list = subdir.split(os.sep)
for file in files:
full_path = os.path.join(subdir, file)
name = os.path.splitext(os.path.basename(file))
id = name[0]
if (tracks['set', 'split'][int(id)] == "training"):
y, sr = librosa.load(full_path)
y_speed = librosa.effects.time_stretch(y, tempo)
out_wav_filename = './AugmentedData/Tempo/' + id + '.wav'
librosa.output.write_wav(out_wav_filename, y_speed, sr=sr)
def Pitch_Shift_Convert(pitch):
AUDIO_DIR = './Samples/'
tracks = utils.load('./fma_metadata/tracks.csv')
try:
os.mkdir('./AugmentedData/Pitch')
except:
print("Pitch Folder Exists. No Creation Necessary")
for subdir, dirs, files in os.walk(AUDIO_DIR):
path_list = subdir.split(os.sep)
for file in files:
full_path = os.path.join(subdir, file)
name = os.path.splitext(os.path.basename(file))
id = name[0]
if (tracks['set', 'split'][int(id)] == "training"):
y, sr = librosa.load(full_path)
y_one = librosa.effects.pitch_shift(y, sr, n_steps=pitch)
out_wav_filename = './AugmentedData/Pitch/' + id + '.wav'
librosa.output.write_wav(out_wav_filename, y_one, sr=sr)
def Spectrogram_Create(WIDTH, HEIGHT, DPI, SONG_DURATION, SR):
tracks = utils.load('./fma_metadata/tracks.csv')
#Spectrograph training/validation/test set
try:
os.mkdir("Data")
except:
print("Data folder exists, skip creation")
try:
os.mkdir("Data/Train")
except:
print("Data/Train folder exists, skip creation")
try:
os.mkdir("Data/Test")
except:
print("Data/Test folder exists, skip creation")
try:
os.mkdir("Data/Validate")
except:
print("Data/Validate folder exists, skip creation")
data_set = tracks['set', 'split']
directory = './Samples'
for subdir, dirs, files in os.walk(directory):
if (subdir != directory):
path_list = subdir.split(os.sep)
print("Begin creating spectrograms for {} genre".format(
path_list[2]))
for file in files:
full_path = os.path.join(subdir, file)
name = os.path.splitext(os.path.basename(file))
id = name[0]
if (tracks['set', 'split'][int(id)] == "test"):
create_spectrogram(full_path, id, "test", WIDTH, HEIGHT,
DPI, SONG_DURATION, SR)
elif (tracks['set', 'split'][int(id)] == "training"):
create_spectrogram(full_path, id, "train", WIDTH, HEIGHT,
DPI, SONG_DURATION, SR)
else:
create_spectrogram(full_path, id, "validate", WIDTH,
HEIGHT, DPI, SONG_DURATION, SR)
print("Finished creating spectrograms for {} genre".format(
path_list[2]))
gc.collect()
#Organized storage of spectrograms
# try:
# os.mkdir('Spectrogram')
# except:
# print("Spectrogram folder exists, skip creation")
#Not for training or testing just to categorize the imgs into their own folders
# for subdir, dirs, files in os.walk(directory):
# if(subdir != directory):
# try:
# path_list = subdir.split(os.sep)
# os.mkdir("Spectrogram/" + path_list[2])
# except:
# print("{} folder already exists, skip creation".format(path_list[2]) )
# print("Begin creating spectrograms for {} genre".format(path_list[2]))
# for file in files:
# full_path = os.path.join(subdir, file)
# name = os.path.splitext(os.path.basename(file))
# id = name[0]
# create_spectrogram(full_path, id, "general")
# print("Finished creating spectrograms for {} genre".format(path_list[2]))