for idx in range(len(unique_labels)):
label2idx[unique_labels[idx]]=int(idx)
lines=open(DATA_FOLDER+'/split'+TOTAL_SPLIT+'/'+CURRRENT_SPLIT+'/'+args.utt2label).readlines()
utt_label = []
for line in lines:
label=line.rstrip().split()[1]
utt_label.append(label2idx[label])
wav_list = []
lines=open(DATA_FOLDER+'/split'+TOTAL_SPLIT+'/'+CURRRENT_SPLIT+'/wav.scp').readlines()
for line in lines:
cols = line.rstrip().split()
wav_list.append(cols[1])
feat, _, utt_shape, tffilename = ft.feat_extract(wav_list,FEAT_TYPE,N_FFT,HOP,VAD,CMVN,EXCLUDE_SHORT,False,DIM,WIN_LENGTH)
if FIXED_LEN>0:
for iter in range(len(feat)):
if feat[iter].shape[0]<=FIXED_LEN:
while feat[iter].shape[0]<=FIXED_LEN:
feat[iter] = np.append(feat[iter],feat[iter],0)
feat[iter] = feat[iter][0:FIXED_LEN,:]
else:
rstart = np.random.randint(0,feat[iter].shape[0]-FIXED_LEN,1)[0]
rend = rstart + FIXED_LEN
feat[iter] = feat[iter][rstart:rend,:]
utt_shape[iter] = np.array(feat[iter].shape)
TFRECORDS_NAME = SAVE_FOLDER+'/'+DATA_FOLDER.split('/')[-1] + '_' + tffilename + '_fixed'+str(FIXED_LEN) + '.' + CURRRENT_SPLIT + '.tfrecords'
lang2idx = {}
for line in lines:
lang = line.rstrip().split()[0]
idx = line.rstrip().split()[1]
lang2idx[lang] = int(idx)
wav_list = []
devid = []
lines = open(DATA_FOLDER + '/wav.scp').readlines()
for line in lines:
cols = line.rstrip().split()
devid.append(cols[0])
wav_list.append(cols[1])
#feature extraction
feat, _, utt_shape, tffilename = ft.feat_extract(wav_list, FEAT_TYPE, N_FFT,
HOP, VAD, CMVN, 0)
#init placeholder
test_feat_batch = tf.placeholder(tf.float32,
[None, None, np.int(INPUT_DIM)],
name="test_feat_batch")
test_label_batch = tf.placeholder(tf.int32, [None], name="test_label_batch")
test_shape_batch = tf.placeholder(tf.int32, [None, 2], name="test_shape_batch")
#init model
emnet_validation = nn_model.nn(test_feat_batch, test_label_batch,
test_label_batch, test_shape_batch, SOFTMAX_NUM,
False, INPUT_DIM, is_batchnorm)
tf.get_variable_scope().reuse_variables()
sess = tf.InteractiveSession()
saver = tf.train.Saver()
RESUME_STARTPOINT = args.resume_startpoint
NN_MODEL = args.model_name
EMBEDDING_LAYER = args.embedding_layer
if VAD =='False':
VAD = False
if CMVN == 'False':
CMVN = False
is_batchnorm = True
if not args.segments_format:
if int(TOTAL_SPLIT)==1:
wavlist,utt_label,spk_label = kd.read_data_list(DATA_FOLDER, utt2spk=True)
else:
wavlist,utt_label,spk_label = kd.read_data_list(DATA_FOLDER+'/split'+TOTAL_SPLIT+'/'+CURRRENT_SPLIT, utt2spk=True)
feat, _, utt_shape, tffilename = ft.feat_extract(wavlist,FEAT_TYPE,N_FFT,HOP,VAD,CMVN,EXCLUDE_SHORT)
else:
if int(TOTAL_SPLIT)==1:
wavlist,utt_label,seg_wavlist,seg_segid,seg_uttid,seg_windows = kd.read_data_list(DATA_FOLDER, utt2spk=False,segments=True)
else:
wavlist,utt_label,seg_wavlist,seg_segid,seg_uttid,seg_windows = kd.read_data_list(DATA_FOLDER+'/split'+TOTAL_SPLIT+'/'+CURRRENT_SPLIT, utt2spk=False,segments=True)
feat, _, utt_shape, tffilename = ft.feat_extract(seg_wavlist,FEAT_TYPE,N_FFT,HOP,VAD,CMVN,EXCLUDE_SHORT,seg_windows=seg_windows)
SAVER_FOLDERNAME = 'saver/'+NN_MODEL+'_'+tffilename
nn_model = __import__(NN_MODEL)
x = tf.placeholder(tf.float32, [None,None,FEAT_DIM])
y = tf.placeholder(tf.int32, [None])
s = tf.placeholder(tf.int32, [None,2])