def load_from_folder(self, resample, use_default_labels):
os.chdir(self.folder_path)
training_files = []
if use_default_labels:
for filename in [f for f in os.listdir('.') if os.path.isfile(f)]:
label = filename.replace('_', ' ').replace('.mp3', '').title()
training_files.append((label, filename))
logger.log("Using %s with label %s" % (filename, label))
else:
resample_prefix = 'resample_'
for filename in [f for f in os.listdir('.') if os.path.isfile(f)]:
print " enter label for '" + filename + "' >"
label = raw_input()
if len(label) == 0: label = filename
target = filename
if resample:
target = resample_prefix + filename
try:
subprocess.call(['/usr/local/bin/lame', '-V5', '--vbr-new', '--resample', '16', filename, target],
stdout=subprocess.PIPE)
generated_name = label.strip().replace(" ", "_").lower() + '.mp3'
subprocess.call(['rm', filename])
subprocess.call(['mv', target, generated_name])
training_files.append((label, generated_name))
except:
logger.warn(" could not resample file '%s'!" % filename)
else:
training_files.append((label, target))
print 'finished resampling!'
self.train_set.data = audio.train(training_files, self.folder_path, self.train_set.config, self.train_set.name, conn_str)
self.train_set.s3_links = []
self.train_set.status = "trained"
self.train_set.save()
return self.train_set._id
def load_from_api(self, resample):
os.chdir(self.folder_path)
training_files = []
try:
for i in range(len(self.train_set.s3_links)):
track = self.train_set.s3_links[i]
label = track['label']
url = track['url']
#filename = track['filename']
print "fetching: ", url
subprocess.call(['curl', '-O', url], stdout=subprocess.PIPE)
filename = url.split('/')[-1]
subprocess.call(['mv', filename, filename + '.mp3'])
filename = filename + '.mp3'
target = filename
if resample:
print "resampling in 16000..."
target = 'resample_' + filename
try:
subprocess.call(['/usr/local/bin/lame', '-V5', '--vbr-new', '--resample', '16', filename, target],
stdout=subprocess.PIPE)
except:
print " could not resample file '%s'!" % filename
training_files.append((label, target))
except:
print " could not do training."
print 'finished resampling!'
self.train_set.data = audio.train(training_files, self.folder_path, self.train_set.config, self.train_set.name, conn_str)
self.train_set.status = "trained"
self.train_set.save()
